From 57bb6cc85a50d372bd4084bbd40325e90af25a19 Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:15:16 +1100 Subject: [PATCH 1/6] Day 5 challenging completed with multilingual with multitone --- .../day5-multi-lingual-desire-format.ipynb | 3585 +++++++++++++++++ 1 file changed, 3585 insertions(+) create mode 100644 week1/community-contributions/day5-multi-lingual-desire-format.ipynb diff --git a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb new file mode 100644 index 0000000..3f1b3ad --- /dev/null +++ b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb @@ -0,0 +1,3585 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "a98030af-fcd1-4d63-a36e-38ba053498fa", + "metadata": {}, + "source": [ + "# A full business solution\n", + "\n", + "## Now we will take our project from Day 1 to the next level\n", + "\n", + "### BUSINESS CHALLENGE:\n", + "\n", + "Create a product that builds a Brochure for a company to be used for prospective clients, investors and potential recruits.\n", + "\n", + "We will be provided a company name and their primary website.\n", + "\n", + "See the end of this notebook for examples of real-world business applications.\n", + "\n", + "And remember: I'm always available if you have problems or ideas! Please do reach out." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "d5b08506-dc8b-4443-9201-5f1848161363", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "# If these fail, please check you're running from an 'activated' environment with (llms) in the command prompt\n", + "\n", + "import os\n", + "import requests\n", + "import json\n", + "from typing import List\n", + "from dotenv import load_dotenv\n", + "from bs4 import BeautifulSoup\n", + "from IPython.display import Markdown, display, update_display\n", + "from openai import OpenAI" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "API key looks good so far\n" + ] + } + ], + "source": [ + "# Initialize and constants\n", + "\n", + "load_dotenv()\n", + "api_key = os.getenv('OPENAI_API_KEY')\n", + "\n", + "if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n", + " print(\"API key looks good so far\")\n", + "else:\n", + " print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n", + " \n", + "MODEL = 'gpt-4o-mini'\n", + "openai = OpenAI()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "106dd65e-90af-4ca8-86b6-23a41840645b", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "\n", + "# Some websites need you to use proper headers when fetching them:\n", + "headers = {\n", + " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n", + "}\n", + "\n", + "class Website:\n", + " \"\"\"\n", + " A utility class to represent a Website that we have scraped, now with links\n", + " \"\"\"\n", + "\n", + " def __init__(self, url):\n", + " self.url = url\n", + " response = requests.get(url, headers=headers)\n", + " self.body = response.content\n", + " soup = BeautifulSoup(self.body, 'html.parser')\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " if soup.body:\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", + " else:\n", + " self.text = \"\"\n", + " links = [link.get('href') for link in soup.find_all('a')]\n", + " self.links = [link for link in links if link]\n", + "\n", + " def get_contents(self):\n", + " return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "e30d8128-933b-44cc-81c8-ab4c9d86589a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['https://edwarddonner.com/',\n", + " 'https://edwarddonner.com/outsmart/',\n", + " 'https://edwarddonner.com/about-me-and-about-nebula/',\n", + " 'https://edwarddonner.com/posts/',\n", + " 'https://edwarddonner.com/',\n", + " 'https://news.ycombinator.com',\n", + " 'https://nebula.io/?utm_source=ed&utm_medium=referral',\n", + " 'https://www.prnewswire.com/news-releases/wynden-stark-group-acquires-nyc-venture-backed-tech-startup-untapt-301269512.html',\n", + " 'https://patents.google.com/patent/US20210049536A1/',\n", + " 'https://www.linkedin.com/in/eddonner/',\n", + " 'https://edwarddonner.com/2024/11/13/llm-engineering-resources/',\n", + " 'https://edwarddonner.com/2024/11/13/llm-engineering-resources/',\n", + " 'https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/',\n", + " 'https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/',\n", + " 'https://edwarddonner.com/2024/08/06/outsmart/',\n", + " 'https://edwarddonner.com/2024/08/06/outsmart/',\n", + " 'https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/',\n", + " 'https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/',\n", + " 'https://edwarddonner.com/',\n", + " 'https://edwarddonner.com/outsmart/',\n", + " 'https://edwarddonner.com/about-me-and-about-nebula/',\n", + " 'https://edwarddonner.com/posts/',\n", + " 'mailto:hello@mygroovydomain.com',\n", + " 'https://www.linkedin.com/in/eddonner/',\n", + " 'https://twitter.com/edwarddonner',\n", + " 'https://www.facebook.com/edward.donner.52']" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ed = Website(\"https://edwarddonner.com\")\n", + "ed.links" + ] + }, + { + "cell_type": "markdown", + "id": "1771af9c-717a-4fca-bbbe-8a95893312c3", + "metadata": {}, + "source": [ + "## First step: Have GPT-4o-mini figure out which links are relevant\n", + "\n", + "### Use a call to gpt-4o-mini to read the links on a webpage, and respond in structured JSON. \n", + "It should decide which links are relevant, and replace relative links such as \"/about\" with \"https://company.com/about\". \n", + "We will use \"one shot prompting\" in which we provide an example of how it should respond in the prompt.\n", + "\n", + "This is an excellent use case for an LLM, because it requires nuanced understanding. Imagine trying to code this without LLMs by parsing and analyzing the webpage - it would be very hard!\n", + "\n", + "Sidenote: there is a more advanced technique called \"Structured Outputs\" in which we require the model to respond according to a spec. We cover this technique in Week 8 during our autonomous Agentic AI project." + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "6957b079-0d96-45f7-a26a-3487510e9b35", + "metadata": {}, + "outputs": [], + "source": [ + "link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n", + "You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n", + "such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n", + "link_system_prompt += \"You should respond in JSON as in this example:\"\n", + "link_system_prompt += \"\"\"\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", + " {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", + " ]\n", + "}\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "b97e4068-97ed-4120-beae-c42105e4d59a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "You are provided with a list of links found on a webpage. You are able to decide which of the links would be most relevant to include in a brochure about the company, such as links to an About page, or a Company page, or Careers/Jobs pages.\n", + "You should respond in JSON as in this example:\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", + " {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", + " ]\n", + "}\n", + "\n" + ] + } + ], + "source": [ + "print(link_system_prompt)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3", + "metadata": {}, + "outputs": [], + "source": [ + "def get_links_user_prompt(website):\n", + " user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n", + " user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n", + "Do not include Terms of Service, Privacy, email links.\\n\"\n", + " user_prompt += \"Links (some might be relative links):\\n\"\n", + " user_prompt += \"\\n\".join(website.links)\n", + " return user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "6bcbfa78-6395-4685-b92c-22d592050fd7", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Here is the list of links on the website of https://edwarddonner.com - please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. Do not include Terms of Service, Privacy, email links.\n", + "Links (some might be relative links):\n", + "https://edwarddonner.com/\n", + "https://edwarddonner.com/outsmart/\n", + "https://edwarddonner.com/about-me-and-about-nebula/\n", + "https://edwarddonner.com/posts/\n", + "https://edwarddonner.com/\n", + "https://news.ycombinator.com\n", + "https://nebula.io/?utm_source=ed&utm_medium=referral\n", + "https://www.prnewswire.com/news-releases/wynden-stark-group-acquires-nyc-venture-backed-tech-startup-untapt-301269512.html\n", + "https://patents.google.com/patent/US20210049536A1/\n", + "https://www.linkedin.com/in/eddonner/\n", + "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", + "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", + "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", + "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", + "https://edwarddonner.com/2024/08/06/outsmart/\n", + "https://edwarddonner.com/2024/08/06/outsmart/\n", + "https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/\n", + "https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/\n", + "https://edwarddonner.com/\n", + "https://edwarddonner.com/outsmart/\n", + "https://edwarddonner.com/about-me-and-about-nebula/\n", + "https://edwarddonner.com/posts/\n", + "mailto:hello@mygroovydomain.com\n", + "https://www.linkedin.com/in/eddonner/\n", + "https://twitter.com/edwarddonner\n", + "https://www.facebook.com/edward.donner.52\n" + ] + } + ], + "source": [ + "print(get_links_user_prompt(ed))" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "a29aca19-ca13-471c-a4b4-5abbfa813f69", + "metadata": {}, + "outputs": [], + "source": [ + "def get_links(url):\n", + " website = Website(url)\n", + " response = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": link_system_prompt},\n", + " {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n", + " ],\n", + " response_format={\"type\": \"json_object\"}\n", + " )\n", + " result = response.choices[0].message.content\n", + " return json.loads(result)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "74a827a0-2782-4ae5-b210-4a242a8b4cc2", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['/',\n", + " '/models',\n", + " '/datasets',\n", + " '/spaces',\n", + " '/posts',\n", + " '/docs',\n", + " '/enterprise',\n", + " '/pricing',\n", + " '/login',\n", + " '/join',\n", + " '/IamCreateAI/Ruyi-Mini-7B',\n", + " '/Datou1111/shou_xin',\n", + " '/answerdotai/ModernBERT-base',\n", + " '/meta-llama/Llama-3.3-70B-Instruct',\n", + " '/tencent/HunyuanVideo',\n", + " '/models',\n", + " '/spaces/JeffreyXiang/TRELLIS',\n", + " '/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute',\n", + " '/spaces/multimodalart/flux-style-shaping',\n", + " '/spaces/Kwai-Kolors/Kolors-Virtual-Try-On',\n", + " '/spaces/lllyasviel/iclight-v2',\n", + " '/spaces',\n", + " '/datasets/fka/awesome-chatgpt-prompts',\n", + " '/datasets/O1-OPEN/OpenO1-SFT',\n", + " '/datasets/HuggingFaceFW/fineweb-2',\n", + " '/datasets/HuggingFaceTB/finemath',\n", + " '/datasets/amphora/QwQ-LongCoT-130K',\n", + " '/datasets',\n", + " '/join',\n", + " '/pricing#endpoints',\n", + " '/pricing#spaces',\n", + " '/pricing',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/allenai',\n", + " '/facebook',\n", + " '/amazon',\n", + " '/google',\n", + " '/Intel',\n", + " '/microsoft',\n", + " '/grammarly',\n", + " '/Writer',\n", + " '/docs/transformers',\n", + " '/docs/diffusers',\n", + " '/docs/safetensors',\n", + " '/docs/huggingface_hub',\n", + " '/docs/tokenizers',\n", + " '/docs/peft',\n", + " '/docs/transformers.js',\n", + " '/docs/timm',\n", + " '/docs/trl',\n", + " '/docs/datasets',\n", + " '/docs/text-generation-inference',\n", + " '/docs/accelerate',\n", + " '/models',\n", + " '/datasets',\n", + " '/spaces',\n", + " '/tasks',\n", + " 'https://ui.endpoints.huggingface.co',\n", + " '/chat',\n", + " '/huggingface',\n", + " '/brand',\n", + " '/terms-of-service',\n", + " '/privacy',\n", + " 'https://apply.workable.com/huggingface/',\n", + " 'mailto:press@huggingface.co',\n", + " '/learn',\n", + " '/docs',\n", + " '/blog',\n", + " 'https://discuss.huggingface.co',\n", + " 'https://status.huggingface.co/',\n", + " 'https://github.com/huggingface',\n", + " 'https://twitter.com/huggingface',\n", + " 'https://www.linkedin.com/company/huggingface/',\n", + " '/join/discord']" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Anthropic has made their site harder to scrape, so I'm using HuggingFace..\n", + "\n", + "huggingface = Website(\"https://huggingface.co\")\n", + "huggingface.links" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'links': [{'type': 'homepage', 'url': 'https://huggingface.co/'},\n", + " {'type': 'about page', 'url': 'https://huggingface.co/huggingface'},\n", + " {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'},\n", + " {'type': 'blog', 'url': 'https://huggingface.co/blog'},\n", + " {'type': 'github page', 'url': 'https://github.com/huggingface'},\n", + " {'type': 'twitter page', 'url': 'https://twitter.com/huggingface'},\n", + " {'type': 'linkedin page',\n", + " 'url': 'https://www.linkedin.com/company/huggingface/'}]}" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "get_links(\"https://huggingface.co\")" + ] + }, + { + "cell_type": "markdown", + "id": "0d74128e-dfb6-47ec-9549-288b621c838c", + "metadata": {}, + "source": [ + "## Second step: make the brochure!\n", + "\n", + "Assemble all the details into another prompt to GPT4-o" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5", + "metadata": {}, + "outputs": [], + "source": [ + "def get_all_details(url):\n", + " result = \"Landing page:\\n\"\n", + " result += Website(url).get_contents()\n", + " links = get_links(url)\n", + " print(\"Found links:\", links)\n", + " for link in links[\"links\"]:\n", + " result += f\"\\n\\n{link['type']}\\n\"\n", + " result += Website(link[\"url\"]).get_contents()\n", + " return result" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "5099bd14-076d-4745-baf3-dac08d8e5ab2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/about'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'company page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'community discussions', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n", + "Landing page:\n", + "Webpage Title:\n", + "Hugging Face – The AI community building the future.\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "The AI community building the future.\n", + "The platform where the machine learning community collaborates on models, datasets, and applications.\n", + "Trending on\n", + "this week\n", + "Models\n", + "IamCreateAI/Ruyi-Mini-7B\n", + "Updated\n", + "4 days ago\n", + "•\n", + "8.17k\n", + "•\n", + "352\n", + "Datou1111/shou_xin\n", + "Updated\n", + "12 days ago\n", + "•\n", + "28.3k\n", + "•\n", + "672\n", + "answerdotai/ModernBERT-base\n", + "Updated\n", + "1 day ago\n", + "•\n", + "6.24k\n", + "•\n", + "236\n", + "meta-llama/Llama-3.3-70B-Instruct\n", + "Updated\n", + "11 days ago\n", + "•\n", + "236k\n", + "•\n", + "1.21k\n", + "tencent/HunyuanVideo\n", + "Updated\n", + "3 days ago\n", + "•\n", + "6.01k\n", + "•\n", + "1.2k\n", + "Browse 400k+ models\n", + "Spaces\n", + "Running\n", + "on\n", + "Zero\n", + "1.79k\n", + "🏢\n", + "TRELLIS\n", + "Scalable and Versatile 3D Generation from images\n", + "Running\n", + "306\n", + "📝\n", + "Scaling test-time compute\n", + "Running\n", + "on\n", + "Zero\n", + "470\n", + "🚀\n", + "Flux Style Shaping\n", + "Optical illusions and style transfer with FLUX\n", + "Running\n", + "on\n", + "CPU Upgrade\n", + "6.11k\n", + "👕\n", + "Kolors Virtual Try-On\n", + "Running\n", + "on\n", + "Zero\n", + "965\n", + "📈\n", + "IC Light V2\n", + "Browse 150k+ applications\n", + "Datasets\n", + "fka/awesome-chatgpt-prompts\n", + "Updated\n", + "Sep 3\n", + "•\n", + "6.83k\n", + "•\n", + "6.58k\n", + "O1-OPEN/OpenO1-SFT\n", + "Updated\n", + "4 days ago\n", + "•\n", + "1.86k\n", + "•\n", + "234\n", + "HuggingFaceFW/fineweb-2\n", + "Updated\n", + "13 days ago\n", + "•\n", + "77.7k\n", + "•\n", + "342\n", + "HuggingFaceTB/finemath\n", + "Updated\n", + "1 day ago\n", + "•\n", + "1.86k\n", + "•\n", + "43\n", + "amphora/QwQ-LongCoT-130K\n", + "Updated\n", + "16 days ago\n", + "•\n", + "1.34k\n", + "•\n", + "85\n", + "Browse 100k+ datasets\n", + "The Home of Machine Learning\n", + "Create, discover and collaborate on ML better.\n", + "The collaboration platform\n", + "Host and collaborate on unlimited public models, datasets and applications.\n", + "Move faster\n", + "With the HF Open source stack.\n", + "Explore all modalities\n", + "Text, image, video, audio or even 3D.\n", + "Build your portfolio\n", + "Share your work with the world and build your ML profile.\n", + "Sign Up\n", + "Accelerate your ML\n", + "We provide paid Compute and Enterprise solutions.\n", + "Compute\n", + "Deploy on optimized\n", + "Inference Endpoints\n", + "or update your\n", + "Spaces applications\n", + "to a GPU in a few clicks.\n", + "View pricing\n", + "Starting at $0.60/hour for GPU\n", + "Enterprise\n", + "Give your team the most advanced platform to build AI with enterprise-grade security, access controls and\n", + "\t\t\tdedicated support.\n", + "Getting started\n", + "Starting at $20/user/month\n", + "Single Sign-On\n", + "Regions\n", + "Priority Support\n", + "Audit Logs\n", + "Resource Groups\n", + "Private Datasets Viewer\n", + "More than 50,000 organizations are using Hugging Face\n", + "Ai2\n", + "Enterprise\n", + "non-profit\n", + "•\n", + "366 models\n", + "•\n", + "1.76k followers\n", + "AI at Meta\n", + "Enterprise\n", + "company\n", + "•\n", + "2.05k models\n", + "•\n", + "3.83k followers\n", + "Amazon Web Services\n", + "company\n", + "•\n", + "21 models\n", + "•\n", + "2.45k followers\n", + "Google\n", + "company\n", + "•\n", + "911 models\n", + "•\n", + "5.76k followers\n", + "Intel\n", + "company\n", + "•\n", + "217 models\n", + "•\n", + "2.07k followers\n", + "Microsoft\n", + "company\n", + "•\n", + "351 models\n", + "•\n", + "6.29k followers\n", + "Grammarly\n", + "company\n", + "•\n", + "10 models\n", + "•\n", + "102 followers\n", + "Writer\n", + "Enterprise\n", + "company\n", + "•\n", + "17 models\n", + "•\n", + "186 followers\n", + "Our Open Source\n", + "We are building the foundation of ML tooling with the community.\n", + "Transformers\n", + "136,571\n", + "State-of-the-art ML for Pytorch, TensorFlow, and JAX.\n", + "Diffusers\n", + "26,740\n", + "State-of-the-art diffusion models for image and audio generation in PyTorch.\n", + "Safetensors\n", + "2,960\n", + "Simple, safe way to store and distribute neural networks weights safely and quickly.\n", + "Hub Python Library\n", + "2,177\n", + "Client library for the HF Hub: manage repositories from your Python runtime.\n", + "Tokenizers\n", + "9,165\n", + "Fast tokenizers, optimized for both research and production.\n", + "PEFT\n", + "16,767\n", + "Parameter efficient finetuning methods for large models.\n", + "Transformers.js\n", + "12,421\n", + "State-of-the-art Machine Learning for the web. Run Transformers directly in your browser, with no need for a server.\n", + "timm\n", + "32,668\n", + "State-of-the-art computer vision models, layers, optimizers, training/evaluation, and utilities.\n", + "TRL\n", + "10,382\n", + "Train transformer language models with reinforcement learning.\n", + "Datasets\n", + "19,378\n", + "Access and share datasets for computer vision, audio, and NLP tasks.\n", + "Text Generation Inference\n", + "9,484\n", + "Toolkit to serve Large Language Models.\n", + "Accelerate\n", + "8,082\n", + "Easily train and use PyTorch models with multi-GPU, TPU, mixed-precision.\n", + "System theme\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Tasks\n", + "Inference Endpoints\n", + "HuggingChat\n", + "Company\n", + "About\n", + "Brand assets\n", + "Terms of service\n", + "Privacy\n", + "Jobs\n", + "Press\n", + "Resources\n", + "Learn\n", + "Documentation\n", + "Blog\n", + "Forum\n", + "Service Status\n", + "Social\n", + "GitHub\n", + "Twitter\n", + "LinkedIn\n", + "Discord\n", + "\n", + "\n", + "\n", + "about page\n", + "Webpage Title:\n", + "about (Sergei)\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Sergei\n", + "about\n", + "Follow\n", + "Kalaipriya's profile picture\n", + "selvivincent's profile picture\n", + "Renumathi's profile picture\n", + "3\n", + "\t\t\t\t\tfollowers\n", + "·\n", + "0 following\n", + "AI & ML interests\n", + "None yet\n", + "Organizations\n", + "None yet\n", + "models\n", + "None public yet\n", + "datasets\n", + "None public yet\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "careers page\n", + "Webpage Title:\n", + "Hugging Face - Current Openings\n", + "Webpage Contents:\n", + "\n", + "\n", + "\n", + "\n", + "blog page\n", + "Webpage Title:\n", + "Hugging Face – Blog\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Blog, Articles, and discussions\n", + "New Article\n", + "Everything\n", + "community\n", + "guide\n", + "open source collab\n", + "partnerships\n", + "research\n", + "NLP\n", + "Audio\n", + "CV\n", + "RL\n", + "ethics\n", + "Diffusion\n", + "Game Development\n", + "RLHF\n", + "Leaderboard\n", + "Case Studies\n", + "Evaluating Audio Reasoning with Big Bench Audio\n", + "By\n", + "mhillsmith\n", + "December 20, 2024\n", + "guest\n", + "•\n", + "8\n", + "Community Articles\n", + "view all\n", + "20+ Free and Paid Digital Marketing Strategies to Automate Repetitive Tasks\n", + "By\n", + "Markets\n", + "•\n", + "about 3 hours ago\n", + "•\n", + "1\n", + "🧠 Tags generation dataset\n", + "By\n", + "zino36\n", + "•\n", + "about 16 hours ago\n", + "•\n", + "1\n", + "AI Agents in Action: Managing GitHub Issues with KaibanJS\n", + "By\n", + "darielnoel\n", + "•\n", + "1 day ago\n", + "**Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs**\n", + "By\n", + "KnutJaegersberg\n", + "•\n", + "1 day ago\n", + "•\n", + "3\n", + "MINERVA: A Multi-Agent LLM System for Digital Scam Protection\n", + "By\n", + "dcarpintero\n", + "•\n", + "2 days ago\n", + "Mastering Iterative Prompting for Optimized AI Code Generation\n", + "By\n", + "luigi12345\n", + "•\n", + "3 days ago\n", + "•\n", + "1\n", + "SILMA RAGQA V1.0: A Comprehensive Benchmark for Evaluating LLMs on RAG QA Use-Cases\n", + "By\n", + "karimouda\n", + "•\n", + "3 days ago\n", + "•\n", + "1\n", + "FuseChat-3.0: Preference Optimization for Implicit Model Fusion\n", + "By\n", + "Wanfq\n", + "•\n", + "3 days ago\n", + "•\n", + "2\n", + "Tutorial: Quantizing Llama 3+ Models for Efficient Deployment\n", + "By\n", + "theeseus-ai\n", + "•\n", + "6 days ago\n", + "•\n", + "3\n", + "How to Expand Your AI Music Generations of 30 Seconds to Several Minutes\n", + "By\n", + "theeseus-ai\n", + "•\n", + "8 days ago\n", + "•\n", + "1\n", + "🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺\n", + "By\n", + "yjernite\n", + "•\n", + "9 days ago\n", + "•\n", + "11\n", + "Building an AI-powered search engine from scratch\n", + "By\n", + "as-cle-bert\n", + "•\n", + "10 days ago\n", + "•\n", + "8\n", + "MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion\n", + "By\n", + "wxDai\n", + "•\n", + "10 days ago\n", + "•\n", + "12\n", + "RLHF 101: A Technical Dive into RLHF\n", + "By\n", + "GitBag\n", + "•\n", + "10 days ago\n", + "•\n", + "4\n", + "[Talk Arena](https://talkarena.org)\n", + "By\n", + "WillHeld\n", + "•\n", + "11 days ago\n", + "•\n", + "1\n", + "Multimodal RAG with Colpali, Milvus and VLMs\n", + "By\n", + "saumitras\n", + "•\n", + "11 days ago\n", + "•\n", + "2\n", + "In Honour of This Year's NeurIPs Test of Time Paper Awardees\n", + "By\n", + "Jaward\n", + "•\n", + "11 days ago\n", + "•\n", + "2\n", + "Power steering: Squeeze massive power from small LLMs\n", + "By\n", + "ucheog\n", + "•\n", + "12 days ago\n", + "•\n", + "4\n", + "Exploring the Power of KaibanJS v0.11.0 🚀\n", + "By\n", + "darielnoel\n", + "•\n", + "12 days ago\n", + "•\n", + "1\n", + "**Building a Custom Retrieval System with Motoko and Node.js**\n", + "By\n", + "theeseus-ai\n", + "•\n", + "12 days ago\n", + "•\n", + "1\n", + "Finally, a Replacement for BERT: Introducing ModernBERT\n", + "By\n", + "bwarner\n", + "December 19, 2024\n", + "guest\n", + "•\n", + "289\n", + "Bamba: Inference-Efficient Hybrid Mamba2 Model\n", + "By\n", + "Linsong-C\n", + "December 18, 2024\n", + "guest\n", + "•\n", + "30\n", + "Welcome the Falcon 3 Family of Open Models!\n", + "By\n", + "FalconLLM\n", + "December 17, 2024\n", + "•\n", + "98\n", + "Benchmarking Language Model Performance on 5th Gen Xeon at GCP\n", + "By\n", + "MatrixYao\n", + "December 17, 2024\n", + "•\n", + "2\n", + "Introducing the Synthetic Data Generator - Build Datasets with Natural Language\n", + "By\n", + "davidberenstein1957\n", + "December 16, 2024\n", + "•\n", + "55\n", + "LeMaterial: an open source initiative to accelerate materials discovery and research\n", + "By\n", + "AlexDuvalinho\n", + "December 10, 2024\n", + "guest\n", + "•\n", + "30\n", + "Hugging Face models in Amazon Bedrock\n", + "By\n", + "pagezyhf\n", + "December 9, 2024\n", + "•\n", + "8\n", + "Open Preference Dataset for Text-to-Image Generation by the 🤗 Community\n", + "By\n", + "davidberenstein1957\n", + "December 9, 2024\n", + "•\n", + "47\n", + "Welcome PaliGemma 2 – New vision language models by Google\n", + "By\n", + "merve\n", + "December 5, 2024\n", + "•\n", + "117\n", + "“How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs\n", + "By\n", + "martin-gorner\n", + "December 5, 2024\n", + "•\n", + "12\n", + "Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard\n", + "By\n", + "alielfilali01\n", + "December 4, 2024\n", + "guest\n", + "•\n", + "26\n", + "Investing in Performance: Fine-tune small models with LLM insights - a CFM case study\n", + "By\n", + "oahouzi\n", + "December 3, 2024\n", + "•\n", + "25\n", + "Rearchitecting Hugging Face Uploads and Downloads\n", + "By\n", + "port8080\n", + "November 26, 2024\n", + "•\n", + "37\n", + "SmolVLM - small yet mighty Vision Language Model\n", + "By\n", + "andito\n", + "November 26, 2024\n", + "•\n", + "142\n", + "Previous\n", + "1\n", + "2\n", + "3\n", + "...\n", + "36\n", + "Next\n", + "Community Articles\n", + "view all\n", + "20+ Free and Paid Digital Marketing Strategies to Automate Repetitive Tasks\n", + "By\n", + "Markets\n", + "•\n", + "about 3 hours ago\n", + "•\n", + "1\n", + "🧠 Tags generation dataset\n", + "By\n", + "zino36\n", + "•\n", + "about 16 hours ago\n", + "•\n", + "1\n", + "AI Agents in Action: Managing GitHub Issues with KaibanJS\n", + "By\n", + "darielnoel\n", + "•\n", + "1 day ago\n", + "**Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs**\n", + "By\n", + "KnutJaegersberg\n", + "•\n", + "1 day ago\n", + "•\n", + "3\n", + "MINERVA: A Multi-Agent LLM System for Digital Scam Protection\n", + "By\n", + "dcarpintero\n", + "•\n", + "2 days ago\n", + "Mastering Iterative Prompting for Optimized AI Code Generation\n", + "By\n", + "luigi12345\n", + "•\n", + "3 days ago\n", + "•\n", + "1\n", + "SILMA RAGQA V1.0: A Comprehensive Benchmark for Evaluating LLMs on RAG QA Use-Cases\n", + "By\n", + "karimouda\n", + "•\n", + "3 days ago\n", + "•\n", + "1\n", + "FuseChat-3.0: Preference Optimization for Implicit Model Fusion\n", + "By\n", + "Wanfq\n", + "•\n", + "3 days ago\n", + "•\n", + "2\n", + "Tutorial: Quantizing Llama 3+ Models for Efficient Deployment\n", + "By\n", + "theeseus-ai\n", + "•\n", + "6 days ago\n", + "•\n", + "3\n", + "How to Expand Your AI Music Generations of 30 Seconds to Several Minutes\n", + "By\n", + "theeseus-ai\n", + "•\n", + "8 days ago\n", + "•\n", + "1\n", + "🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺\n", + "By\n", + "yjernite\n", + "•\n", + "9 days ago\n", + "•\n", + "11\n", + "Building an AI-powered search engine from scratch\n", + "By\n", + "as-cle-bert\n", + "•\n", + "10 days ago\n", + "•\n", + "8\n", + "MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion\n", + "By\n", + "wxDai\n", + "•\n", + "10 days ago\n", + "•\n", + "12\n", + "RLHF 101: A Technical Dive into RLHF\n", + "By\n", + "GitBag\n", + "•\n", + "10 days ago\n", + "•\n", + "4\n", + "[Talk Arena](https://talkarena.org)\n", + "By\n", + "WillHeld\n", + "•\n", + "11 days ago\n", + "•\n", + "1\n", + "Multimodal RAG with Colpali, Milvus and VLMs\n", + "By\n", + "saumitras\n", + "•\n", + "11 days ago\n", + "•\n", + "2\n", + "In Honour of This Year's NeurIPs Test of Time Paper Awardees\n", + "By\n", + "Jaward\n", + "•\n", + "11 days ago\n", + "•\n", + "2\n", + "Power steering: Squeeze massive power from small LLMs\n", + "By\n", + "ucheog\n", + "•\n", + "12 days ago\n", + "•\n", + "4\n", + "Exploring the Power of KaibanJS v0.11.0 🚀\n", + "By\n", + "darielnoel\n", + "•\n", + "12 days ago\n", + "•\n", + "1\n", + "**Building a Custom Retrieval System with Motoko and Node.js**\n", + "By\n", + "theeseus-ai\n", + "•\n", + "12 days ago\n", + "•\n", + "1\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "company page\n", + "Webpage Title:\n", + "huggingface (Hugging Face)\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Hugging Face\n", + "Enterprise\n", + "company\n", + "Verified\n", + "https://huggingface.co\n", + "huggingface\n", + "huggingface\n", + "Activity Feed\n", + "Follow\n", + "8,542\n", + "AI & ML interests\n", + "The AI community building the future.\n", + "Recent Activity\n", + "IAMJB\n", + "updated\n", + "a dataset\n", + "9 minutes ago\n", + "huggingface/community-science-paper-v2\n", + "IAMJB\n", + "updated\n", + "a dataset\n", + "about 6 hours ago\n", + "huggingface/paper-central-data\n", + "fdaudens\n", + "updated\n", + "a Space\n", + "about 19 hours ago\n", + "huggingface/open-source-ai-year-in-review-2024\n", + "View all activity\n", + "Team members\n", + "224\n", + "+190\n", + "+177\n", + "+156\n", + "+146\n", + "+126\n", + "Organization Card\n", + "Community\n", + "About org cards\n", + "👋 Hi!\n", + "We are on a mission to democratize\n", + "good\n", + "machine learning, one commit at a time.\n", + "If that sounds like something you should be doing, why don't you\n", + "join us\n", + "!\n", + "For press enquiries, you can\n", + "✉️ contact our team here\n", + ".\n", + "Collections\n", + "1\n", + "DistilBERT release\n", + "Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.\n", + "distilbert/distilbert-base-cased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6\n", + "•\n", + "358k\n", + "•\n", + "35\n", + "distilbert/distilbert-base-uncased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6\n", + "•\n", + "14.8M\n", + "•\n", + "577\n", + "distilbert/distilbert-base-multilingual-cased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6\n", + "•\n", + "472k\n", + "•\n", + "148\n", + "distilbert/distilbert-base-uncased-finetuned-sst-2-english\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Dec 19, 2023\n", + "•\n", + "6.96M\n", + "•\n", + "•\n", + "645\n", + "spaces\n", + "23\n", + "Sort: \n", + "\t\tRecently updated\n", + "pinned\n", + "Running\n", + "52\n", + "📈\n", + "Number Tokenization Blog\n", + "Running\n", + "395\n", + "😻\n", + "Open Source Ai Year In Review 2024\n", + "What happened in open-source AI this year, and what’s next?\n", + "Running\n", + "42\n", + "🔋\n", + "Inference Playground\n", + "Running\n", + "196\n", + "⚡\n", + "paper-central\n", + "Running\n", + "on\n", + "TPU v5e\n", + "6\n", + "💬\n", + "Keras Chatbot Battle\n", + "Running\n", + "101\n", + "⚡\n", + "Modelcard Creator\n", + "Expand 23\n", + "\t\t\t\t\t\t\tspaces\n", + "models\n", + "18\n", + "Sort: \n", + "\t\tRecently updated\n", + "huggingface/test-gating-group-2\n", + "Updated\n", + "4 days ago\n", + "huggingface/test-gating-group-1\n", + "Updated\n", + "4 days ago\n", + "huggingface/timesfm-tourism-monthly\n", + "Updated\n", + "12 days ago\n", + "•\n", + "29\n", + "•\n", + "1\n", + "huggingface/CodeBERTa-language-id\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Mar 29\n", + "•\n", + "1.14k\n", + "•\n", + "54\n", + "huggingface/falcon-40b-gptq\n", + "Text Generation\n", + "•\n", + "Updated\n", + "Jun 14, 2023\n", + "•\n", + "19\n", + "•\n", + "12\n", + "huggingface/autoformer-tourism-monthly\n", + "Updated\n", + "May 24, 2023\n", + "•\n", + "1.5k\n", + "•\n", + "9\n", + "huggingface/distilbert-base-uncased-finetuned-mnli\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Mar 22, 2023\n", + "•\n", + "1.37k\n", + "•\n", + "2\n", + "huggingface/informer-tourism-monthly\n", + "Updated\n", + "Feb 24, 2023\n", + "•\n", + "1.12k\n", + "•\n", + "5\n", + "huggingface/time-series-transformer-tourism-monthly\n", + "Updated\n", + "Feb 23, 2023\n", + "•\n", + "2.16k\n", + "•\n", + "18\n", + "huggingface/the-no-branch-repo\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "Feb 10, 2023\n", + "•\n", + "7\n", + "•\n", + "3\n", + "Expand 18\n", + "\t\t\t\t\t\t\tmodels\n", + "datasets\n", + "31\n", + "Sort: \n", + "\t\tRecently updated\n", + "huggingface/community-science-paper-v2\n", + "Viewer\n", + "•\n", + "Updated\n", + "9 minutes ago\n", + "•\n", + "5.03k\n", + "•\n", + "404\n", + "•\n", + "7\n", + "huggingface/paper-central-data\n", + "Viewer\n", + "•\n", + "Updated\n", + "about 6 hours ago\n", + "•\n", + "119k\n", + "•\n", + "553\n", + "•\n", + "8\n", + "huggingface/documentation-images\n", + "Viewer\n", + "•\n", + "Updated\n", + "1 day ago\n", + "•\n", + "44\n", + "•\n", + "2.43M\n", + "•\n", + "43\n", + "huggingface/transformers-metadata\n", + "Viewer\n", + "•\n", + "Updated\n", + "2 days ago\n", + "•\n", + "1.52k\n", + "•\n", + "559\n", + "•\n", + "14\n", + "huggingface/diffusers-metadata\n", + "Viewer\n", + "•\n", + "Updated\n", + "2 days ago\n", + "•\n", + "62\n", + "•\n", + "442\n", + "•\n", + "4\n", + "huggingface/policy-docs\n", + "Updated\n", + "3 days ago\n", + "•\n", + "898\n", + "•\n", + "6\n", + "huggingface/my-distiset-3f5a230e\n", + "Updated\n", + "30 days ago\n", + "•\n", + "17\n", + "huggingface/cookbook-images\n", + "Viewer\n", + "•\n", + "Updated\n", + "Nov 14\n", + "•\n", + "1\n", + "•\n", + "40.1k\n", + "•\n", + "6\n", + "huggingface/vllm-metadata\n", + "Updated\n", + "Oct 8\n", + "•\n", + "12\n", + "huggingface/paper-central-data-2\n", + "Viewer\n", + "•\n", + "Updated\n", + "Oct 4\n", + "•\n", + "58.3k\n", + "•\n", + "68\n", + "•\n", + "2\n", + "Expand 31\n", + "\t\t\t\t\t\t\tdatasets\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "community discussions\n", + "Webpage Title:\n", + "Hugging Face Forums - Hugging Face Community Discussion\n", + "Webpage Contents:\n", + "Loading\n", + "Hugging Face Forums\n", + "Topic\n", + "Replies\n", + "Views\n", + "Activity\n", + "List of `size_categories`\n", + "🤗Datasets\n", + "3\n", + "5\n", + "December 21, 2024\n", + "Feature request - maintain list of favorite hf pages reachable from my hom epage\n", + "Site Feedback\n", + "4\n", + "886\n", + "December 21, 2024\n", + "404 error on carbon emission calculation\n", + "Site Feedback\n", + "1\n", + "7\n", + "December 21, 2024\n", + "Cannot connect gRPC Server Hosted on HuggingFace Spaces\n", + "Spaces\n", + "0\n", + "8\n", + "December 21, 2024\n", + "Hide system prompt or system instruction\n", + "Beginners\n", + "3\n", + "15\n", + "December 21, 2024\n", + "ModuleNotFoundError: No module named 'huggingface_hub.inference._types'\n", + "🤗Hub\n", + "0\n", + "5\n", + "December 21, 2024\n", + "Understanding State Management with Gradio and LangGraph\n", + "Beginners\n", + "1\n", + "11\n", + "December 21, 2024\n", + "Dimension problem\n", + "Beginners\n", + "25\n", + "21\n", + "December 21, 2024\n", + "Fine-tuning whisper on sound-event-detection dataset\n", + "🤗Transformers\n", + "0\n", + "4\n", + "December 20, 2024\n", + "Model that can generate both text and image as output\n", + "Research\n", + "4\n", + "42\n", + "December 21, 2024\n", + "Lm studio and Chat ui doesn't work with module\n", + "Beginners\n", + "11\n", + "33\n", + "December 21, 2024\n", + "Inference API Context Window and TOS\n", + "Beginners\n", + "0\n", + "12\n", + "December 20, 2024\n", + "Talkie AI got remove from app store -any alternative ai chat?\n", + "Beginners\n", + "4\n", + "1151\n", + "December 18, 2024\n", + "Inference Text Generation API issue\n", + "Intermediate\n", + "0\n", + "7\n", + "December 20, 2024\n", + "From Pandas Dataframe to Huggingface Dataset\n", + "Beginners\n", + "9\n", + "60459\n", + "December 20, 2024\n", + "\"Load Diffusion Model\" and \"Unet Loader (GGUF)\" null/undefined\n", + "Beginners\n", + "6\n", + "200\n", + "December 20, 2024\n", + "Timeout Issue with DeepSpeed on Multiple GPUs\n", + "DeepSpeed\n", + "0\n", + "8\n", + "December 20, 2024\n", + "Spaces dedicated gpu limit\n", + "Spaces\n", + "1\n", + "14\n", + "December 19, 2024\n", + "Chatbot PDF - using flan-t5-large model\n", + "Models\n", + "0\n", + "7\n", + "December 20, 2024\n", + "Gateway Problem\n", + "Beginners\n", + "0\n", + "8\n", + "December 20, 2024\n", + "RT-DETR attention map dimension - PekingU/rtdetr_r50vd\n", + "Models\n", + "0\n", + "5\n", + "December 20, 2024\n", + "Extending the tokenizer affects model generation\n", + "Intermediate\n", + "3\n", + "9\n", + "December 19, 2024\n", + "How to Ensure Each Process Reads Its Own Dataset and Trains Correctly When Using Trainer?\n", + "🤗Transformers\n", + "0\n", + "5\n", + "December 20, 2024\n", + "Can't save the tensorflow model of nvidia/mit-b5\n", + "Intermediate\n", + "3\n", + "127\n", + "December 19, 2024\n", + "# Audio course Unit 4. sample code not working. Can anyone check for me? Thanks\n", + "Course\n", + "0\n", + "6\n", + "December 20, 2024\n", + "Host Models on Hugging face and Perform Inference on Hugging Face Infrastructure\n", + "Beginners\n", + "0\n", + "6\n", + "December 20, 2024\n", + "Torchrun, trainer, dataset setup\n", + "Intermediate\n", + "4\n", + "71\n", + "December 20, 2024\n", + "Training fails on multiple GPUs with RuntimeError 'chuck expects at least a 1-dimensional array'\n", + "Beginners\n", + "2\n", + "108\n", + "December 19, 2024\n", + "How do you know whether the model is merged and uploaded?\n", + "Intermediate\n", + "0\n", + "11\n", + "December 20, 2024\n", + "Qwen based AI assistant randomly having an absolute, utter, complete 'mental breakdowns'?? (Inference API)\n", + "🤗Transformers\n", + "2\n", + "23\n", + "December 17, 2024\n", + "next page →\n", + "Home\n", + "Categories\n", + "Guidelines\n", + "Terms of Service\n", + "Privacy Policy\n", + "Powered by\n", + "Discourse\n", + ", best viewed with JavaScript enabled\n", + "\n", + "\n", + "\n", + "GitHub page\n", + "Webpage Title:\n", + "Hugging Face · GitHub\n", + "Webpage Contents:\n", + "Skip to content\n", + "Navigation Menu\n", + "Toggle navigation\n", + "Sign in\n", + "huggingface\n", + "Product\n", + "GitHub Copilot\n", + "Write better code with AI\n", + "Security\n", + "Find and fix vulnerabilities\n", + "Actions\n", + "Automate any workflow\n", + "Codespaces\n", + "Instant dev environments\n", + "Issues\n", + "Plan and track work\n", + "Code Review\n", + "Manage code changes\n", + "Discussions\n", + "Collaborate outside of code\n", + "Code Search\n", + "Find more, search less\n", + "Explore\n", + "All features\n", + "Documentation\n", + "GitHub Skills\n", + "Blog\n", + "Solutions\n", + "By company size\n", + "Enterprises\n", + "Small and medium teams\n", + "Startups\n", + "By use case\n", + "DevSecOps\n", + "DevOps\n", + "CI/CD\n", + "View all use cases\n", + "By industry\n", + "Healthcare\n", + "Financial services\n", + "Manufacturing\n", + "Government\n", + "View all industries\n", + "View all solutions\n", + "Resources\n", + "Topics\n", + "AI\n", + "DevOps\n", + "Security\n", + "Software Development\n", + "View all\n", + "Explore\n", + "Learning Pathways\n", + "White papers, Ebooks, Webinars\n", + "Customer Stories\n", + "Partners\n", + "Executive Insights\n", + "Open Source\n", + "GitHub Sponsors\n", + "Fund open source developers\n", + "The ReadME Project\n", + "GitHub community articles\n", + "Repositories\n", + "Topics\n", + "Trending\n", + "Collections\n", + "Enterprise\n", + "Enterprise platform\n", + "AI-powered developer platform\n", + "Available add-ons\n", + "Advanced Security\n", + "Enterprise-grade security features\n", + "GitHub Copilot\n", + "Enterprise-grade AI features\n", + "Premium Support\n", + "Enterprise-grade 24/7 support\n", + "Pricing\n", + "Search or jump to...\n", + "Search code, repositories, users, issues, pull requests...\n", + "Search\n", + "Clear\n", + "Search syntax tips\n", + "Provide feedback\n", + "We read every piece of feedback, and take your input very seriously.\n", + "Include my email address so I can be contacted\n", + "Cancel\n", + "Submit feedback\n", + "Saved searches\n", + "Use saved searches to filter your results more quickly\n", + "Cancel\n", + "Create saved search\n", + "Sign in\n", + "Sign up\n", + "Reseting focus\n", + "You signed in with another tab or window.\n", + "Reload\n", + "to refresh your session.\n", + "You signed out in another tab or window.\n", + "Reload\n", + "to refresh your session.\n", + "You switched accounts on another tab or window.\n", + "Reload\n", + "to refresh your session.\n", + "Dismiss alert\n", + "Hugging Face\n", + "The AI community building the future.\n", + "Verified\n", + "We've verified that the organization\n", + "huggingface\n", + "controls the domain:\n", + "huggingface.co\n", + "Learn more about verified organizations\n", + "40.1k\n", + "followers\n", + "NYC + Paris\n", + "https://huggingface.co/\n", + "X\n", + "@huggingface\n", + "Overview\n", + "Repositories\n", + "Projects\n", + "Packages\n", + "People\n", + "Sponsoring\n", + "0\n", + "More\n", + "Overview\n", + "Repositories\n", + "Projects\n", + "Packages\n", + "People\n", + "Sponsoring\n", + "Pinned\n", + "Loading\n", + "transformers\n", + "transformers\n", + "Public\n", + "🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.\n", + "Python\n", + "137k\n", + "27.3k\n", + "diffusers\n", + "diffusers\n", + "Public\n", + "🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.\n", + "Python\n", + "26.7k\n", + "5.5k\n", + "datasets\n", + "datasets\n", + "Public\n", + "🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools\n", + "Python\n", + "19.4k\n", + "2.7k\n", + "peft\n", + "peft\n", + "Public\n", + "🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.\n", + "Python\n", + "16.8k\n", + "1.7k\n", + "accelerate\n", + "accelerate\n", + "Public\n", + "🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support\n", + "Python\n", + "8.1k\n", + "995\n", + "optimum\n", + "optimum\n", + "Public\n", + "🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools\n", + "Python\n", + "2.6k\n", + "486\n", + "Repositories\n", + "Loading\n", + "Type\n", + "Select type\n", + "Forks\n", + "Archived\n", + "Mirrors\n", + "Templates\n", + "Language\n", + "Select language\n", + "All\n", + "C\n", + "C#\n", + "C++\n", + "Cuda\n", + "Dockerfile\n", + "Go\n", + "Handlebars\n", + "HTML\n", + "Java\n", + "JavaScript\n", + "Jupyter Notebook\n", + "Kotlin\n", + "Lua\n", + "MDX\n", + "Mustache\n", + "Nix\n", + "Python\n", + "Rust\n", + "Shell\n", + "Smarty\n", + "Swift\n", + "TypeScript\n", + "Sort\n", + "Select order\n", + "Last updated\n", + "Name\n", + "Stars\n", + "Showing 10 of 275 repositories\n", + "trl\n", + "Public\n", + "Train transformer language models with reinforcement learning.\n", + "huggingface/trl’s past year of commit activity\n", + "Python\n", + "10,382\n", + "Apache-2.0\n", + "1,337\n", + "106\n", + "46\n", + "Updated\n", + "Dec 21, 2024\n", + "transformers.js\n", + "Public\n", + "State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!\n", + "huggingface/transformers.js’s past year of commit activity\n", + "JavaScript\n", + "12,421\n", + "Apache-2.0\n", + "790\n", + "274\n", + "(3 issues need help)\n", + "48\n", + "Updated\n", + "Dec 21, 2024\n", + "diffusers\n", + "Public\n", + "🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.\n", + "huggingface/diffusers’s past year of commit activity\n", + "Python\n", + "26,740\n", + "Apache-2.0\n", + "5,504\n", + "379\n", + "(10 issues need help)\n", + "169\n", + "Updated\n", + "Dec 21, 2024\n", + "text-generation-inference\n", + "Public\n", + "Large Language Model Text Generation Inference\n", + "huggingface/text-generation-inference’s past year of commit activity\n", + "Python\n", + "9,484\n", + "Apache-2.0\n", + "1,106\n", + "152\n", + "21\n", + "Updated\n", + "Dec 21, 2024\n", + "candle\n", + "Public\n", + "Minimalist ML framework for Rust\n", + "huggingface/candle’s past year of commit activity\n", + "Rust\n", + "16,103\n", + "Apache-2.0\n", + "980\n", + "344\n", + "(5 issues need help)\n", + "86\n", + "Updated\n", + "Dec 21, 2024\n", + "autotrain-advanced\n", + "Public\n", + "🤗 AutoTrain Advanced\n", + "huggingface/autotrain-advanced’s past year of commit activity\n", + "Python\n", + "4,157\n", + "Apache-2.0\n", + "505\n", + "16\n", + "2\n", + "Updated\n", + "Dec 21, 2024\n", + "transformers\n", + "Public\n", + "🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.\n", + "huggingface/transformers’s past year of commit activity\n", + "Python\n", + "136,571\n", + "Apache-2.0\n", + "27,342\n", + "1,003\n", + "(2 issues need help)\n", + "526\n", + "Updated\n", + "Dec 21, 2024\n", + "lighteval\n", + "Public\n", + "Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends\n", + "huggingface/lighteval’s past year of commit activity\n", + "Python\n", + "889\n", + "MIT\n", + "109\n", + "62\n", + "(1 issue needs help)\n", + "15\n", + "Updated\n", + "Dec 21, 2024\n", + "hub-docs\n", + "Public\n", + "Docs of the Hugging Face Hub\n", + "huggingface/hub-docs’s past year of commit activity\n", + "Handlebars\n", + "309\n", + "Apache-2.0\n", + "259\n", + "90\n", + "25\n", + "Updated\n", + "Dec 21, 2024\n", + "optimum-habana\n", + "Public\n", + "Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)\n", + "huggingface/optimum-habana’s past year of commit activity\n", + "Python\n", + "162\n", + "Apache-2.0\n", + "219\n", + "11\n", + "(1 issue needs help)\n", + "40\n", + "Updated\n", + "Dec 21, 2024\n", + "View all repositories\n", + "People\n", + "View all\n", + "Top languages\n", + "Python\n", + "Jupyter Notebook\n", + "Rust\n", + "TypeScript\n", + "JavaScript\n", + "Most used topics\n", + "pytorch\n", + "machine-learning\n", + "nlp\n", + "deep-learning\n", + "transformers\n", + "Footer\n", + "© 2024 GitHub, Inc.\n", + "Footer navigation\n", + "Terms\n", + "Privacy\n", + "Security\n", + "Status\n", + "Docs\n", + "Contact\n", + "Manage cookies\n", + "Do not share my personal information\n", + "You can’t perform that action at this time.\n", + "\n", + "\n", + "\n", + "Twitter page\n", + "Webpage Title:\n", + "x.com\n", + "Webpage Contents:\n", + "\n", + "\n", + "\n", + "\n", + "LinkedIn page\n", + "Webpage Title:\n", + "Hugging Face | LinkedIn\n", + "Webpage Contents:\n", + "Skip to main content\n", + "LinkedIn\n", + "Articles\n", + "People\n", + "Learning\n", + "Jobs\n", + "Games\n", + "Get the app\n", + "Join now\n", + "Sign in\n", + "Hugging Face\n", + "Software Development\n", + "The AI community building the future.\n", + "See jobs\n", + "Follow\n", + "Discover all 472 employees\n", + "Report this company\n", + "About us\n", + "The AI community building the future.\n", + "Website\n", + "https://huggingface.co\n", + "External link for Hugging Face\n", + "Industry\n", + "Software Development\n", + "Company size\n", + "51-200 employees\n", + "Type\n", + "Privately Held\n", + "Founded\n", + "2016\n", + "Specialties\n", + "machine learning, natural language processing, and deep learning\n", + "Products\n", + "Hugging Face\n", + "Hugging Face\n", + "Natural Language Processing (NLP) Software\n", + "We‚Äôre on a journey to solve and democratize artificial intelligence through natural language.\n", + "Locations\n", + "Primary\n", + "Get directions\n", + "Paris, FR\n", + "Get directions\n", + "Employees at Hugging Face\n", + "Ludovic Huraux\n", + "Bassem ASSEH\n", + "Rajat Arya\n", + "Tech Lead & Software Engineer @ HF | prev: co-founder XetHub, Apple, Turi, AWS, Microsoft\n", + "Jeff Boudier\n", + "Product + Growth at Hugging Face\n", + "See all employees\n", + "Updates\n", + "Hugging Face\n", + "reposted this\n", + "Gradio\n", + "47,326 followers\n", + "7h\n", + "Report this post\n", + "NOW you can add AI to your Slack, Discord in just few steps with Gradio!ü§©\n", + "\n", + "üî•Create Slack apps, Discord bots, or Intercom-style website widgets in ANY modality (Text, image, Video, Audio, Omni etc)! Keep reading to learn how ‚¨áÔ∏è\n", + "\n", + "Guide: üöÄ Creating a Slack Bot from a Gradio App üöÄ\n", + "Read here:\n", + "https://lnkd.in/g2_Bydrj\n", + "ü§éDo you love building stuff with Gradio? Support us on GitHub:\n", + "Gradio.dev\n", + "‚Ķmore\n", + "50\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Daniel V.\n", + "Machine Learning Librarian@ü§ó | Championing Open Science & Machine Learning\n", + "21h\n", + "Report this post\n", + "Introducing FineWeb-C üåêüéì, a community-built dataset for improving language models in ALL languages. \n", + "\n", + "Inspired by FineWeb-Edu the community is labelling the educational quality of texts for many languages. \n", + "\n", + "318 annotators, 32K+ annotations, 12 languages - and growing!üåç\n", + "57\n", + "2 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Merve Noyan\n", + "open-sourceress at ü§ó | Google Developer Expert in Machine Learning, MSc Candidate in Data Science\n", + "22h\n", + "Report this post\n", + "Fine-tune ColPali for your multimodal RAG use case üî•\n", + "\n", + "ColPali just landed to\n", + "Hugging Face\n", + "transformers and I have built a simple fine-tuning tutorial with QLoRA ü§ó\n", + "You can fine-tune the model with 32 GB VRAM with batch size of 4 (which can run on Colab A100)\n", + "Link in comments üí¨\n", + "267\n", + "4 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "ü§ñ Avthar Sewrathan\n", + "AI and Developer Product Leader | I talk about using AI and building AI apps\n", + "1d\n", + "Report this post\n", + "TIL: You can now load any\n", + "Hugging Face\n", + "dataset into PostgreSQL with just 1 line of SQL ü§Ø\n", + "\n", + "All thanks to the pgai PostgreSQL extension. \n", + "\n", + "Shoutout to\n", + "Matvey Arye\n", + "from the\n", + "Timescale\n", + "AI engineering team for implementing this.\n", + "\n", + "Learn more about using PostgreSQL with HuggingFace datasets in the HuggingFace docs:\n", + "https://lnkd.in/eS4hqSDq\n", + "#postgresql\n", + "#huggingface\n", + "#opensource\n", + "180\n", + "14 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Argilla\n", + "10,266 followers\n", + "1d\n", + "Report this post\n", + "üé¢ Push to Hub: Export your dataset to the Hugging Face Hub directly from the Argilla UI.\n", + "\n", + "We‚Äôre super excited to announce that we've closed the loop: now you can load a dataset from the Hub, open it on\n", + "Argilla\n", + "UI, label it, and push the annotated dataset to the Hub. All this without a line of code!\n", + "\n", + "\n", + "ùó™ùóµùòÜ ùòÄùóµùóºùòÇùóπùó± ùòÜùóºùòÇ ùòÇùòÄùó≤ ùó∂ùòÅ?\n", + "\n", + "Your AI project's impact depends heavily on the effort and care you put into your data. This new feature enables you to iterate faster and make annotated data available in the right format for training and evaluation.\n", + "\n", + "\n", + "ùóõùóºùòÑ ùó±ùóºùó≤ùòÄ ùó∂ùòÅ ùòÑùóºùóøùó∏?\n", + "\n", + "1Ô∏è‚É£ Import initial data from a CSV or any format to Hugging Face\n", + "2Ô∏è‚É£ Load it into the Argilla UI and configure the annotation task\n", + "3Ô∏è‚É£ Annotate your dataset\n", + "üöÄ Click on ‚ÄúPush to Hub‚Äù and share the dataset with your team (or the entire world)\n", + "\n", + "üëâ ùó•ùó≤ùóÆùó±ùòÜ ùòÅùóº ùòÅùóøùòÜ ùó∂ùòÅ ùóºùòÇùòÅ?\n", + "\n", + "Get started here:\n", + "https://lnkd.in/dhA-swR5\n", + "Release highlights:\n", + "https://lnkd.in/dbdQXG-W\n", + "35\n", + "3 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Daniel V.\n", + "Machine Learning Librarian@ü§ó | Championing Open Science & Machine Learning\n", + "1d\n", + "Report this post\n", + "Hot take: shipping BERT-sized models in 2025 will benefit far more people than sharing an LLM overfitted to some saturated leaderboards \n", + "\n", + "We're already seeing ModernBERT finetunes on the\n", + "Hugging Face\n", + "Hub. My guess is we'll see hundreds of these by the end of 2025.\n", + "80\n", + "4 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Gradio\n", + "47,326 followers\n", + "1d\n", + "Edited\n", + "Report this post\n", + "ü§Øüî•LEARN HOW TO CREATE interactive agentic chatbots using Gradio that are capable of showcasing the Thoughts, Tasks, and interim responses of Multiple Agents as you await the final answer from your AI assistant.\n", + "\n", + "üéØ Customer Support multi-agents with\n", + "CrewAI\n", + "and\n", + "Gradio\n", + "Showcasing here, a user-friendly, high-performing multi-agent gradio app. TO operate it, simply enter a webpage URL along with your questions related to that page, and in turn receive a high-quality response from the CrewAI Multi-Agent setup.\n", + "\n", + "üöÄAccess this app on\n", + "Hugging Face\n", + "Spaces:\n", + "https://lnkd.in/g6kXp_D2\n", + "‚Ķmore\n", + "72\n", + "1 Comment\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Clem Delangue ü§ó\n", + "Clem Delangue ü§ó is an Influencer\n", + "Co-founder & CEO at Hugging Face\n", + "2d\n", + "Report this post\n", + "In the past few months, we've invested a lot of efforts in improving the user management features of the Hugging Face hub that more than 5M AI builder are now using. It helps not only for easier organization collaboration but also for security (for example to make sure ex team members don't still have access to private models). \n", + "\n", + "If your manager, VP AI or admin/CISO is not aware, mention them below so that we can connect if they have any questions or feedback as most of these features are part of the Enterprise hub subscriptions:\n", + "https://lnkd.in/e-RY-3vs\n", + ")\n", + "\n", + "Cheers!\n", + "47\n", + "3 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Clem Delangue ü§ó\n", + "Clem Delangue ü§ó is an Influencer\n", + "Co-founder & CEO at Hugging Face\n", + "4d\n", + "Report this post\n", + "Just 10 days after o1's public debut, we‚Äôre thrilled to unveil the open-source version of the groundbreaking technique behind its success: scaling test-time compute ü߆üí° \n", + "\n", + "By giving models more \"time to think,\" Llama 1B outperforms Llama 8B in math‚Äîbeating a model 8x its size. The full recipe is open-sourceü§Ø \n", + "\n", + "This is the power of open science and open-source AI! üåç‚ú®\n", + "5,292\n", + "125 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Hugging Face\n", + "reposted this\n", + "Philipp Schmid\n", + "Technical Lead & LLMs at Hugging Face ü§ó | AWS ML HERO ü¶∏ü誂ôÇÔ∏è\n", + "1d\n", + "Report this post\n", + "ModernBERT, BERT revisited in the age of LLMs and Generative AI!\n", + "LightOn\n", + "and\n", + "Answer.ai\n", + "modernized BERT! Improved architecture with 8192 context length, flash attention, and trained on 2T tokens. ModernBERT outperforms version BERT and RoBERTa versions! üëÄ\n", + "\n", + "TL;DR;\n", + "2Ô∏è‚É£¬†Comes in 2 sizes base (139M) and large (395M)\n", + "üöĬ†Better performance across all metrics than the original BERT\n", + "üìè 8,192 token context length (16x longer than BERT)\n", + "‚ö° Modern architecture with Flash Attention 2, RoPE embeddings, and alternating attention\n", + "üìö Trained on 2 trillion tokens, primarily English and Code\n", + "üí® 2-4x faster than other models with mixed-length inputs\n", + "üî쬆Released under Apache 2.0\n", + "ü§ó¬†Available on\n", + "Hugging Face\n", + "and Transformers (main)\n", + "\n", + "Models:\n", + "https://lnkd.in/ethiJ2xh\n", + "Blog:\n", + "https://lnkd.in/ebiEzb4P\n", + "Paper:\n", + "https://lnkd.in/ezR8MUBF\n", + "1,844\n", + "67 Comments\n", + "Like\n", + "Comment\n", + "Share\n", + "Join now to see what you are missing\n", + "Find people you know at Hugging Face\n", + "Browse recommended jobs for you\n", + "View all updates, news, and articles\n", + "Join now\n", + "Similar pages\n", + "Anthropic\n", + "Research Services\n", + "Mistral AI\n", + "Technology, Information and Internet\n", + "Paris, France\n", + "OpenAI\n", + "Research Services\n", + "San Francisco, CA\n", + "LangChain\n", + "Technology, Information and Internet\n", + "Perplexity\n", + "Software Development\n", + "San Francisco, California\n", + "Generative AI\n", + "Technology, Information and Internet\n", + "Google DeepMind\n", + "Research Services\n", + "London, London\n", + "LlamaIndex\n", + "Technology, Information and Internet\n", + "San Francisco, California\n", + "DeepLearning.AI\n", + "Software Development\n", + "Palo Alto, California\n", + "Cohere\n", + "Software Development\n", + "Toronto, Ontario\n", + "Show more similar pages\n", + "Show fewer similar pages\n", + "Browse jobs\n", + "Engineer jobs\n", + "555,845 open jobs\n", + "Machine Learning Engineer jobs\n", + "148,937 open jobs\n", + "Scientist jobs\n", + "48,969 open jobs\n", + "Software Engineer jobs\n", + "300,699 open jobs\n", + "Intern jobs\n", + "71,196 open jobs\n", + "Developer jobs\n", + "258,935 open jobs\n", + "Analyst jobs\n", + "694,057 open jobs\n", + "Intelligence Specialist jobs\n", + "7,156 open jobs\n", + "Manager jobs\n", + "1,880,925 open jobs\n", + "Data Scientist jobs\n", + "264,158 open jobs\n", + "Director jobs\n", + "1,220,357 open jobs\n", + "Associate jobs\n", + "1,091,945 open jobs\n", + "Python Developer jobs\n", + "46,642 open jobs\n", + "Evangelist jobs\n", + "5,068 open jobs\n", + "Data Engineer jobs\n", + "192,126 open jobs\n", + "Vice President jobs\n", + "235,270 open jobs\n", + "Quantitative Analyst jobs\n", + "19,570 open jobs\n", + "Program Manager jobs\n", + "243,900 open jobs\n", + "Data Science Specialist jobs\n", + "2,441 open jobs\n", + "Lead Software Engineer jobs\n", + "68,215 open jobs\n", + "Show more jobs like this\n", + "Show fewer jobs like this\n", + "Funding\n", + "Hugging Face\n", + "7 total rounds\n", + "Last Round\n", + "Series D\n", + "Feb 16, 2024\n", + "External Crunchbase Link for last round of funding\n", + "See more info on\n", + "crunchbase\n", + "More searches\n", + "More searches\n", + "Engineer jobs\n", + "Intern jobs\n", + "Machine Learning Engineer jobs\n", + "Software Engineer jobs\n", + "Scientist jobs\n", + "Developer jobs\n", + "Research Intern jobs\n", + "Analyst jobs\n", + "Intelligence Specialist jobs\n", + "Quantitative Analyst jobs\n", + "Technician jobs\n", + "Data Science Specialist jobs\n", + "Project Manager jobs\n", + "Summer Intern jobs\n", + "Manager jobs\n", + "Senior Staff Engineer jobs\n", + "PHD jobs\n", + "Trader jobs\n", + "Researcher jobs\n", + "Data Scientist jobs\n", + "Writer jobs\n", + "Data Analyst jobs\n", + "Product Designer jobs\n", + "Back End Developer jobs\n", + "Spring Intern jobs\n", + "Program Manager jobs\n", + "Technology Officer jobs\n", + "Software Intern jobs\n", + "Security Professional jobs\n", + "Senior Software Engineer jobs\n", + "Python Developer jobs\n", + "Engineering Manager jobs\n", + "Web Developer jobs\n", + "Graduate jobs\n", + "Full Stack Engineer jobs\n", + "Professor jobs\n", + "Head jobs\n", + "Verification Manager jobs\n", + "User Experience Designer jobs\n", + "Recruiter jobs\n", + "Chief Executive Officer jobs\n", + "Associate jobs\n", + "Support Developer jobs\n", + "Senior Firmware Engineer jobs\n", + "Marketing Manager jobs\n", + "Modeling Engineer jobs\n", + "Designer jobs\n", + "Automation Lead jobs\n", + "Options Trader jobs\n", + "Agile Coach jobs\n", + "Research Engineer jobs\n", + "Software Quality Assurance Analyst jobs\n", + "User Experience Manager jobs\n", + "Technical Intern jobs\n", + "Junior Network Engineer jobs\n", + "Information Technology Recruiter jobs\n", + "User Researcher jobs\n", + "Player jobs\n", + "Engineering Project Manager jobs\n", + "Digital Strategist jobs\n", + "LinkedIn\n", + "© 2024\n", + "About\n", + "Accessibility\n", + "User Agreement\n", + "Privacy Policy\n", + "Cookie Policy\n", + "Copyright Policy\n", + "Brand Policy\n", + "Guest Controls\n", + "Community Guidelines\n", + "ÿߟÑÿπÿ±ÿ®Ÿäÿ© (Arabic)\n", + "‡¶¨‡¶æ‡¶Ç‡¶≤‡¶æ (Bangla)\n", + "ƒåe≈°tina (Czech)\n", + "Dansk (Danish)\n", + "Deutsch (German)\n", + "ŒïŒªŒªŒ∑ŒΩŒπŒ∫Œ¨ (Greek)\n", + "English (English)\n", + "Espa√±ol (Spanish)\n", + "ŸÅÿßÿ±ÿ≥€å (Persian)\n", + "Suomi (Finnish)\n", + "Fran√ßais (French)\n", + "‡§π‡§ø‡§Ç‡§¶‡•Ä (Hindi)\n", + "Magyar (Hungarian)\n", + "Bahasa Indonesia (Indonesian)\n", + "Italiano (Italian)\n", + "◊¢◊ë◊®◊ô◊™ (Hebrew)\n", + "Êó•Êú¨Ë™û (Japanese)\n", + "Ìïú͵≠Ïñ¥ (Korean)\n", + "‡§Æ‡§∞‡§æ‡§†‡•Ä (Marathi)\n", + "Bahasa Malaysia (Malay)\n", + "Nederlands (Dutch)\n", + "Norsk (Norwegian)\n", + "‡®™‡©∞‡®ú‡®æ‡®¨‡©Ä (Punjabi)\n", + "Polski (Polish)\n", + "Portugu√™s (Portuguese)\n", + "Rom√¢nƒÉ (Romanian)\n", + "–†—É—Å—Å–∫–∏–π (Russian)\n", + "Svenska (Swedish)\n", + "‡∞§‡±Ü‡∞≤‡±Å‡∞ó‡±Å (Telugu)\n", + "‡∏†‡∏≤‡∏©‡∏≤‡πч∏ó‡∏¢ (Thai)\n", + "Tagalog (Tagalog)\n", + "T√ºrk√ße (Turkish)\n", + "–£–∫—Ä–∞—ó–Ω—Å—å–∫–∞ (Ukrainian)\n", + "Ti·∫øng Vi·ªát (Vietnamese)\n", + "ÁÆÄ‰Ωì‰∏≠Êñá (Chinese (Simplified))\n", + "Ê≠£È´î‰∏≠Êñá (Chinese (Traditional))\n", + "Language\n", + "Agree & Join LinkedIn\n", + "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", + "User Agreement\n", + ",\n", + "Privacy Policy\n", + ", and\n", + "Cookie Policy\n", + ".\n", + "Sign in to see who you already know at Hugging Face\n", + "Sign in\n", + "Welcome back\n", + "Email or phone\n", + "Password\n", + "Show\n", + "Forgot password?\n", + "Sign in\n", + "or\n", + "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", + "User Agreement\n", + ",\n", + "Privacy Policy\n", + ", and\n", + "Cookie Policy\n", + ".\n", + "New to LinkedIn?\n", + "Join now\n", + "or\n", + "New to LinkedIn?\n", + "Join now\n", + "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", + "User Agreement\n", + ",\n", + "Privacy Policy\n", + ", and\n", + "Cookie Policy\n", + ".\n", + "LinkedIn\n", + "LinkedIn is better on the app\n", + "Don‚Äôt have the app? Get it in the Microsoft Store.\n", + "Open the app\n", + "\n", + "\n" + ] + } + ], + "source": [ + "print(get_all_details(\"https://huggingface.co\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2", + "metadata": {}, + "outputs": [], + "source": [ + "system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", + "and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", + "Include details of company culture, customers and careers/jobs if you have the information.\"\n", + "\n", + "# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n", + "\n", + "# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", + "# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", + "# Include details of company culture, customers and careers/jobs if you have the information.\"\n" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23", + "metadata": {}, + "outputs": [], + "source": [ + "def get_brochure_user_prompt(company_name, url):\n", + " user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n", + " user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n", + " user_prompt += get_all_details(url)\n", + " user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n", + " return user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "cd909e0b-1312-4ce2-a553-821e795d7572", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog', 'url': 'https://huggingface.co/blog'}, {'type': 'company page', 'url': 'https://huggingface.co/enterprise'}]}\n", + "You are looking at a company called: HuggingFace\n", + "Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\n", + "Landing page:\n", + "Webpage Title:\n", + "Hugging Face – The AI community building the future.\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "The AI community building the future.\n", + "The platform where the machine learning community collaborates on models, datasets, and applications.\n", + "Trending on\n", + "this week\n", + "Models\n", + "IamCreateAI/Ruyi-Mini-7B\n", + "Updated\n", + "4 days ago\n", + "•\n", + "8.17k\n", + "•\n", + "352\n", + "Datou1111/shou_xin\n", + "Updated\n", + "12 days ago\n", + "•\n", + "28.3k\n", + "•\n", + "672\n", + "answerdotai/ModernBERT-base\n", + "Updated\n", + "1 day ago\n", + "•\n", + "6.24k\n", + "•\n", + "236\n", + "meta-llama/Llama-3.3-70B-Instruct\n", + "Updated\n", + "11 days ago\n", + "•\n", + "236k\n", + "•\n", + "1.21k\n", + "tencent/HunyuanVideo\n", + "Updated\n", + "3 days ago\n", + "•\n", + "6.01k\n", + "•\n", + "1.2k\n", + "Browse 400k+ models\n", + "Spaces\n", + "Running\n", + "on\n", + "Zero\n", + "1.79k\n", + "🏢\n", + "TRELLIS\n", + "Scalable and Versatile 3D Generation from images\n", + "Running\n", + "306\n", + "📝\n", + "Scaling test-time compute\n", + "Running\n", + "on\n", + "Zero\n", + "470\n", + "🚀\n", + "Flux Style Shaping\n", + "Optical illusions and style transfer with FLUX\n", + "Running\n", + "on\n", + "CPU Upgrade\n", + "6.11k\n", + "👕\n", + "Kolors Virtual Try-On\n", + "Running\n", + "on\n", + "Zero\n", + "965\n", + "📈\n", + "IC Light V2\n", + "Browse 150k+ applications\n", + "Datasets\n", + "fka/awesome-chatgpt-prompts\n", + "Updated\n", + "Sep 3\n", + "•\n", + "6.83k\n", + "•\n", + "6.58k\n", + "O1-OPEN/OpenO1-SFT\n", + "Updated\n", + "4 days ago\n", + "•\n", + "1.86k\n", + "•\n", + "234\n", + "HuggingFaceFW/fineweb-2\n", + "Updated\n", + "13 days ago\n", + "•\n", + "77.7k\n", + "•\n", + "342\n", + "HuggingFaceTB/finemath\n", + "Updated\n", + "1 day ago\n", + "•\n", + "1.86k\n", + "•\n", + "43\n", + "amphora/QwQ-LongCoT-130K\n", + "Updated\n", + "16 days ago\n", + "•\n", + "1.34k\n", + "•\n", + "85\n", + "Browse 100k+ datasets\n", + "The Home of Machine Learning\n", + "Create, discover and collaborate on ML better.\n", + "The collaboration platform\n", + "Host and collaborate on unlimited public models, datasets and applications.\n", + "Move faster\n", + "With the HF Open source stack.\n", + "Explore all modalities\n", + "Text, image, video, audio or even 3D.\n", + "Build your portfolio\n", + "Share your work with the world and build your ML profile.\n", + "Sign Up\n", + "Accelerate your ML\n", + "We provide paid Compute and Enterprise solutions.\n", + "Compute\n", + "Deploy on optimized\n", + "Inference Endpoints\n", + "or update your\n", + "Spaces applications\n", + "to a GPU in a few clicks.\n", + "View pricing\n", + "Starting at $0.60/hour for GPU\n", + "Enterprise\n", + "Give your team the most advanced platform to build AI with enterprise-grade security, access controls and\n", + "\t\t\tdedicated support.\n", + "Getting started\n", + "Starting at $20/user/month\n", + "Single Sign-On\n", + "Regions\n", + "Priority Support\n", + "Audit Logs\n", + "Resource Groups\n", + "Private Datasets Viewer\n", + "More than 50,000 organizations are using Hugging Face\n", + "Ai2\n", + "Enterprise\n", + "non-profit\n", + "•\n", + "366 models\n", + "•\n", + "1.76k followers\n", + "AI at Meta\n", + "Enterprise\n", + "company\n", + "•\n", + "2.05k models\n", + "•\n", + "3.83k followers\n", + "Amazon Web Services\n", + "company\n", + "•\n", + "21 models\n", + "•\n", + "2.45k followers\n", + "Google\n", + "company\n", + "•\n", + "911 models\n", + "•\n", + "5.76k followers\n", + "Intel\n", + "company\n", + "•\n", + "217 models\n", + "•\n", + "2.07k followers\n", + "Microsoft\n", + "company\n", + "•\n", + "351 models\n", + "•\n", + "6.29k followers\n", + "Grammarly\n", + "company\n", + "•\n", + "10 models\n", + "•\n", + "102 followers\n", + "Writer\n", + "Enterprise\n", + "company\n", + "•\n", + "17 models\n", + "•\n", + "186 followers\n", + "Our Open Source\n", + "We are building the foundation of ML tooling with the community.\n", + "Transformers\n", + "136,571\n", + "State-of-the-art ML for Pytorch, TensorFlow, and JAX.\n", + "Diffusers\n", + "26,740\n", + "State-of-the-art diffusion models for image and audio generation in PyTorch.\n", + "Safetensors\n", + "2,960\n", + "Simple, safe way to store and distribute neural networks weights safely and quickly.\n", + "Hub Python Library\n", + "2,177\n", + "Client library for the HF Hub: manage repositories from your Python runtime.\n", + "Tokenizers\n", + "9,165\n", + "Fast tokenizers, optimized for both research and production.\n", + "PEFT\n", + "16,767\n", + "Parameter efficient finetuning methods for large models.\n", + "Transformers.js\n", + "12,421\n", + "State-of-the-art Machine Learning for the web. Run Transformers directly in your browser, with no need for a server.\n", + "timm\n", + "32,668\n", + "State-of-the-art computer vision models, layers, optimizers, training/evaluation, and utilities.\n", + "TRL\n", + "10,382\n", + "Train transformer language models with reinforcement learning.\n", + "Datasets\n", + "19,378\n", + "Access and share datasets for computer vision, audio, and NLP tasks.\n", + "Text Generation Inference\n", + "9,484\n", + "Toolkit to serve Large Language Models.\n", + "Accelerate\n", + "8,082\n", + "Easily train and use PyTorch models with multi-GPU, TPU, mixed-precision.\n", + "System theme\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Tasks\n", + "Inference Endpoints\n", + "HuggingChat\n", + "Company\n", + "About\n", + "Brand assets\n", + "Terms of service\n", + "Privacy\n", + "Jobs\n", + "Press\n", + "Resources\n", + "Learn\n", + "Documentation\n", + "Blog\n", + "Forum\n", + "Service Status\n", + "Social\n", + "GitHub\n", + "Twitter\n", + "LinkedIn\n", + "Discord\n", + "\n", + "\n", + "\n", + "about page\n", + "Webpage Title:\n", + "Hugging Face – The AI community building the future.\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "The AI community building the future.\n", + "The platform where the machine learning community collaborates on models, datasets, and applications.\n", + "Trending on\n", + "this week\n", + "Models\n", + "IamCreateAI/Ruyi-Mini-7B\n", + "Updated\n", + "4 days ago\n", + "•\n", + "8.17k\n", + "•\n", + "352\n", + "Datou1111/shou_xin\n", + "Updated\n", + "12 days ago\n", + "•\n", + "28.3k\n", + "•\n", + "672\n", + "answerdotai/ModernBERT-base\n", + "Updated\n", + "1 day ago\n", + "•\n", + "6.24k\n", + "•\n", + "236\n", + "meta-llama/Llama-3.3-70B-Instruct\n", + "Updated\n", + "11 days ago\n", + "•\n", + "236k\n", + "•\n", + "1.21k\n", + "tencent/HunyuanVideo\n", + "Updated\n", + "3 days ago\n", + "•\n", + "6.01k\n", + "•\n", + "1.2k\n", + "Browse 400k+ models\n", + "Spaces\n", + "Running\n", + "on\n", + "Zero\n", + "1.79k\n", + "🏢\n", + "TRELLIS\n", + "Scalable and Versatile 3D Generation from images\n", + "\n" + ] + } + ], + "source": [ + "print(get_brochure_user_prompt(\"HuggingFace\", \"https://huggingface.co\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46", + "metadata": {}, + "outputs": [], + "source": [ + "def create_brochure(company_name, url):\n", + " response = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", + " ],\n", + " )\n", + " result = response.choices[0].message.content\n", + " display(Markdown(result))" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "e093444a-9407-42ae-924a-145730591a39", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'home page', 'url': 'https://huggingface.com/'}, {'type': 'about page', 'url': 'https://huggingface.com/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.com/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.com/pricing'}, {'type': 'blog page', 'url': 'https://huggingface.com/blog'}, {'type': 'community page', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "# Hugging Face Brochure\n", + "\n", + "**Hugging Face** \n", + "*The AI community building the future.*\n", + "\n", + "---\n", + "\n", + "## About Us\n", + "Hugging Face is a pioneering platform where the machine learning community comes together to collaborate on models, datasets, and applications. With over 400,000 models and 100,000 datasets available, we empower users to create, discover, and innovate in the field of machine learning.\n", + "\n", + "### Our Mission\n", + "To accelerate the development and deployment of machine learning applications, making cutting-edge technology accessible to everyone.\n", + "\n", + "---\n", + "\n", + "## Company Culture\n", + "At Hugging Face, we believe in the power of collaboration and open-source technology. We foster an inclusive environment where every team member's input is valued, allowing for diverse ideas and perspectives. Our culture emphasizes continuous learning, innovation, and a commitment to advancing AI for the greater good.\n", + "\n", + "---\n", + "\n", + "## Customers\n", + "Hugging Face serves more than 50,000 organizations, including industry leaders such as:\n", + "\n", + "- **Amazon Web Services**\n", + "- **Meta**\n", + "- **Google**\n", + "- **Microsoft**\n", + "- **Intel**\n", + " \n", + "These organizations utilize our platform for various machine learning tasks, enhancing their workflows and outputs.\n", + "\n", + "---\n", + "\n", + "## Careers at Hugging Face\n", + "We are always on the lookout for talented individuals who are passionate about AI and machine learning. Career opportunities at Hugging Face offer:\n", + "\n", + "- A collaborative work environment\n", + "- Remote work flexibility\n", + "- Continuing education and mentorship\n", + "- Opportunities to work on impactful projects\n", + "\n", + "**Join us and help shape the future of AI!**\n", + "\n", + "---\n", + "\n", + "## Our Offerings\n", + "### Models\n", + "- Access over 400,000 machine learning models, covering a variety of tasks and technologies.\n", + "\n", + "### Datasets\n", + "- Discover and share 100,000+ datasets tailored for computer vision, audio, and NLP tasks.\n", + "\n", + "### Spaces\n", + "- Utilize our application space to run various applications including real-time projects and demonstrations.\n", + "\n", + "### Enterprise Solutions\n", + "- With dedicated support and industry-grade security, our Enterprise solutions are designed for organizations looking to implement AI at scale.\n", + "\n", + "---\n", + "\n", + "## Get Started Today!\n", + "**Sign up now** to become part of the Hugging Face community and access an array of tools to accelerate your machine learning journey. \n", + "[Sign Up Here](#)\n", + "\n", + "---\n", + "\n", + "**Stay Connected** \n", + "Follow us on our social media platforms:\n", + "- [GitHub](#)\n", + "- [Twitter](#)\n", + "- [LinkedIn](#)\n", + "- [Discord](#)\n", + "\n", + "**Hugging Face – Building the Future of AI**" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "create_brochure(\"HuggingFace\", \"https://huggingface.com\")" + ] + }, + { + "cell_type": "markdown", + "id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18", + "metadata": {}, + "source": [ + "## Finally - a minor improvement\n", + "\n", + "With a small adjustment, we can change this so that the results stream back from OpenAI,\n", + "with the familiar typewriter animation" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "51db0e49-f261-4137-aabe-92dd601f7725", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_brochure(company_name, url):\n", + " stream = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", + " ],\n", + " stream=True\n", + " )\n", + " \n", + " response = \"\"\n", + " display_handle = display(Markdown(\"\"), display_id=True)\n", + " for chunk in stream:\n", + " response += chunk.choices[0].delta.content or ''\n", + " response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n", + " update_display(Markdown(response), display_id=display_handle.display_id)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'community discussion', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "# Welcome to Hugging Face\n", + "\n", + "## The AI Community Building the Future\n", + "\n", + "At Hugging Face, we bring together the machine learning community to collaborate on groundbreaking models, datasets, and applications. Our platform is a vibrant hub where innovation meets practicality, empowering developers and researchers to create state-of-the-art AI solutions.\n", + "\n", + "---\n", + "\n", + "### 🏆 What We Offer\n", + "\n", + "- **Models**: Access and discover over **400k+ models** including the latest advancements in AI.\n", + "- **Datasets**: A rich collection of **100k+ datasets** tailored for various machine learning tasks.\n", + "- **Spaces**: Collaborate on applications and projects seamlessly within our community’s creative workspace.\n", + "\n", + "---\n", + "\n", + "### 🌏 Our Customers\n", + "\n", + "Join the ranks of **50,000+ organizations** leveraging Hugging Face’s offerings, including industry giants like:\n", + "- **Meta**\n", + "- **Amazon Web Services**\n", + "- **Google**\n", + "- **Microsoft**\n", + "- **Grammarly**\n", + "\n", + "These companies trust us to accelerate their machine learning initiatives and foster innovation.\n", + "\n", + "---\n", + "\n", + "### 🌱 Company Culture\n", + "\n", + "At Hugging Face, we embrace an open-source ethos, encouraging collaboration and contribution from the community. Our culture is centered around creativity, innovation, and inclusivity. We believe in empowering individuals and teams by providing the right tools and support to shape the future of AI.\n", + "\n", + "---\n", + "\n", + "### 🚀 Careers at Hugging Face\n", + "\n", + "We are on the lookout for passionate individuals to join our team! If you share our vision of an accessible AI landscape, explore the career opportunities we offer. We provide an environment that supports academic growth, teamwork, and professional development while making a meaningful impact in the machine learning realm.\n", + "\n", + "#### Current Openings Include:\n", + "- Machine Learning Engineers\n", + "- Data Scientists\n", + "- Software Developers\n", + "- Community Managers\n", + "\n", + "---\n", + "\n", + "### 💡 Join Us\n", + "\n", + "Are you ready to be part of a revolution in AI? **[Sign Up](#)** today to explore the possibilities with Hugging Face or **[Log In](#)** if you’re already part of our community.\n", + "\n", + "Let’s build the future of AI together!\n", + "\n", + "---\n", + "\n", + "*For inquiries about our enterprise solutions, pricing, or community involvement, feel free to reach out through our website.* \n", + "\n", + "**Connect with us:** \n", + "[Twitter](#) | [LinkedIn](#) | [GitHub](#) | [Forum](#)" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "87bd1188", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'homepage', 'url': 'https://huggingface.co/'}, {'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'discussion forum', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "\n", + "# Hugging Face: The AI Community Building the Future\n", + "\n", + "Welcome to Hugging Face, the leading collaborative platform for the machine learning community. With a robust environment designed for creating, discovering, and deploying machine learning models, datasets, and applications, Hugging Face is at the frontier of artificial intelligence innovation. \n", + "\n", + "---\n", + "\n", + "## About Us\n", + "At Hugging Face, we believe in the power of collaboration. Our platform enables users to work together on projects that range from machine-learning models to expansive datasets. With over 400,000 models and 100,000 datasets available, we provide the tools necessary to help researchers, developers, and organizations accelerate their machine learning projects.\n", + "\n", + "- **Trending Models This Week:**\n", + " - **IamCreateAI/Ruyi-Mini-7B** | 8.17k | Updated 4 days ago\n", + " - **Datou1111/shou_xin** | 28.3k | Updated 12 days ago\n", + " - **meta-llama/Llama-3.3-70B-Instruct** | 236k | Updated 11 days ago\n", + "\n", + "Explore our community-driven approach that integrates state-of-the-art tools like Transformers, DiffUsers, and PEFT (Parameter Efficient Finetuning).\n", + "\n", + "---\n", + "\n", + "## Company Culture\n", + "Hugging Face fosters a vibrant and inclusive company culture, aiming to empower individuals and teams through transparent practices and open-source methodologies. We believe in “AI for everyone,” promoting accessibility and co-creation within the AI community. \n", + "\n", + "### Why Work With Us?\n", + "- **Collaborative Environment**: Join a diverse team of experts and enthusiasts dedicated to pushing the boundaries of AI and machine learning.\n", + "- **Open Source Commitment**: Contribute to freely accessible tools that serve the global community.\n", + "- **Flexible Work**: We support remote work and provide a range of job opportunities tailored to different areas of expertise.\n", + "\n", + "---\n", + "\n", + "## Customers & Organizations\n", + "Over 50,000 organizations utilize Hugging Face in various industries, including notable names such as:\n", + "- **Meta AI**\n", + "- **Amazon Web Services**\n", + "- **Google**\n", + "- **Microsoft**\n", + "\n", + "Our enterprise solutions offer seamless integration with advanced security features, making us a trusted partner for both startups and established corporations.\n", + "\n", + "---\n", + "\n", + "## Careers at Hugging Face\n", + "We are always on the lookout for passionate individuals to join our team. Explore our open positions in areas such as software development, research, marketing, and customer support.\n", + "\n", + "- **Open Positions**: \n", + " - Machine Learning Engineer\n", + " - Data Scientist\n", + " - Community Manager\n", + "\n", + "Join us in shaping the future of AI. \n", + "\n", + "**[Explore Careers](#)**\n", + "\n", + "---\n", + "\n", + "## Join the Hugging Face Community\n", + "Whether you're looking to develop cutting-edge AI models, contribute to open-source projects, or advance your career in this dynamic field, Hugging Face is your gateway to innovation.\n", + "\n", + "**[Learn More](#)** | **[Sign Up Today](#)**\n", + "\n", + "Together, let's build the future of AI!\n", + "\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "markdown", + "id": "a9e7375d", + "metadata": {}, + "source": [ + "## **Multi-lingual with Desire Format**\n" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "af5c959f", + "metadata": {}, + "outputs": [], + "source": [ + "def multi_lingual_stream_brochure(company_name, url, language, tone):\n", + "\n", + " system_prompt = f\"\"\"\n", + "You are an assistant that analyzes the contents of several relevant pages from a company website and creates a visually appealing and professional short brochure for prospective customers, investors, and recruits. \n", + "The brochure should be written in {language} and use a {tone.lower()} tone throughout.\n", + "\n", + "The brochure should follow this structure (in {language}):\n", + "\n", + "1. **Front Cover**:\n", + " - Prominently display the company name as Title.\n", + " - Include a compelling headline or tagline.\n", + " - Add something engaging relevant to the company’s mission.\n", + "\n", + "2. **About Us**:\n", + " - Provide a brief introduction to the company.\n", + " - State the company’s core mission and vision.\n", + " - Mention the founding story or key milestones.\n", + "\n", + "3. **What We Offer**:\n", + " - Summarize the company's products, services, or solutions.\n", + " - Highlight benefits or unique selling points.\n", + " - Include testimonials or case studies if available.\n", + "\n", + "4. **Our Culture**:\n", + " - Outline the company’s key values or guiding principles.\n", + " - Describe the workplace environment (e.g., innovation-driven, inclusive, collaborative).\n", + " - Highlight community engagement or CSR initiatives.\n", + "\n", + "5. **Who We Serve**:\n", + " - Describe the target customers or industries served.\n", + " - Mention notable clients or partners.\n", + " - Include testimonials or endorsements from customers.\n", + "\n", + "6. **Join Us**:\n", + " - Detail career or internship opportunities.\n", + " - Highlight benefits, career growth, or training opportunities.\n", + " - Provide direct links or steps to apply.\n", + "\n", + "7. **Contact Us**:\n", + " - Provide the company’s address, phone number, and email.\n", + " - Include links to social media platforms.\n", + " - Add a link to the company’s website.\n", + "\n", + "8. **Closing Note**:\n", + " - End with a thank-you message or an inspirational note for the reader.\n", + " - Add a call-to-action (e.g., “Get in touch today!” or “Explore more on our website”).\n", + "\n", + "Ensure the content is concise, engaging, visually clear, and tailored to the target audience. Use headings and subheadings to make the brochure easy to navigate. Include links and contact information wherever applicable.\n", + "\"\"\"\n", + "\n", + "\n", + " \n", + " stream = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", + " ],\n", + " stream=True\n", + " )\n", + " \n", + " response = \"\"\n", + " display_handle = display(Markdown(\"\"), display_id=True)\n", + " for chunk in stream:\n", + " response += chunk.choices[0].delta.content or ''\n", + " response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n", + " update_display(Markdown(response), display_id=display_handle.display_id)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "744bfc05", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://openai.com/about'}, {'type': 'careers page', 'url': 'https://openai.com/careers'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "It seems that the landing and related pages for OpenAI did not yield any specific content. However, I can create a creative and engaging brochure based on general knowledge about OpenAI. Here's a humorous and entertaining brochure written in Urdu:\n", + "\n", + "\n", + "# 🎉 اوپن اے آئی: ہوشیار robots کا دوست! 🎉\n", + "\n", + "---\n", + "\n", + "## About Us - ہمارے بارے میں:\n", + "\n", + "ہماری کمپنی اوپن اے آئی، 2015 میں بنی۔ ہم نے سوچا کہ \"کیوں نہ ایک ایسا انٹیلیجنٹ سسٹم بنائیں جو انسانوں کی مدد کرے؟\" تو ہم نے کام شروع کیا اور دیکھیں! ہم نے ایک نئی دنیا کی بنیاد رکھی۔ ہماری مشن ہے \"تمام لوگوں کے لئے AI کی طاقت کو قابل رسائی بنانا\"۔ آفاقی طاقت کو ڈھونڈتے ہیں، جیسے آپ کے فرج میں چھپے ہوئے برگر!\n", + "\n", + "---\n", + "\n", + "## What We Offer - ہم کیا پیش کرتے ہیں:\n", + "\n", + "ہم AI کے شوقین ہیں! 🤖 ہم مختلف پروڈکٹس اور سروسز پیش کرتے ہیں، جیسے کہ:\n", + "\n", + "- **GPT-3**: آپ کے سوالات کے جواب دینے کے لئے تیار!\n", + "- **تخلیقی تحریر**: جنریٹنگ آئیڈیاز جب آپ کی تخلیقیت بریک ہو جائے!\n", + "- **AI ٹولز**: آپ کی زندگی کو مزید آسان بنانے کے لئے!\n", + "\n", + "ہمارے صارفین کہتے ہیں، \"اپنی زندگی میں اوپن اے آئی کی ضرورت ہے، جیسے موٹیویشن کی ضرورت ہوتی ہے!\"\n", + "\n", + "---\n", + "\n", + "## Our Culture - ہماری ثقافت:\n", + "\n", + "ہماری کمپنی میں، ہمارا بنیادی اصول ہے: \"پیار اور انوکھا خیالات!\" 🤗 ہم نے انوکھے، تعاون پر مبنی ماحول کی بنیاد رکھی، جہاں ہر کوئی اپنی بات کہہ سکتا ہے، یہاں تک کہ ونڈو کے باہر کھڑا درخت بھی! ہم کمیونٹی کی خدمت کیلئے ہمیشہ تیار رہتے ہیں، وہ بھی سوشل میڈٰیا پر۔\n", + "\n", + "---\n", + "\n", + "## Who We Serve - ہم کس کی خدمت کرتے ہیں:\n", + "\n", + "ہم ہر اُس شخص کی خدمت کرتے ہیں جو سوپر ہیرومنٹ کی تلاش میں ہے۔ ہمارے وزیٹر، محققین، اور ٹیکنالوجی کے شوقین ہیں، اور ہمارے بہترین کلائنٹس include شامل ہیں \"بڑا دماغی جیسا سوچنے والے!\" 💡\n", + "\n", + "---\n", + "\n", + "## Join Us - ہمارے ساتھ شامل ہوں:\n", + "\n", + "آپ کو ترقی کی تلاش ہے؟ تو ہماری ٹیم کا حصہ بنیں! 🚀 ہم ہمیشہ نئے امریکی جاموں کی تلاش میں ہیں۔ آپ کو ٹریننگ، ترقی کے مواقع، اور سہولیات فراہم کریں گے۔\n", + "\n", + "📩 **درخواست دینے کے مرحلے:** ہماری ویب سائٹ پر جائیں، کیونکہ ہم جانتے ہیں کہ آپ کا خواب آپ کے قریب ہے!\n", + "\n", + "---\n", + "\n", + "## Contact Us - ہم سے رابطہ کریں:\n", + "\n", + "**پتہ:** نیٹ ورک کی دنیا \n", + "**فون:** 123-456-789 \n", + "**ایمیل:** info@openai.com \n", + "**سوشل میڈیا:** [فیس بک](#) | [ٹویٹر](#) | [لنکڈ ان](#) \n", + "**ویب سائٹ:** [openai.com](#)\n", + "\n", + "---\n", + "\n", + "## Closing Note - اختتامی نوٹ:\n", + "\n", + "ہماری کمپنی اوپن اے آئی کی طرف سے ایک شکریہ! اے آئی کی دنیا میں قدم رکھنے کا وقت آ گیا ہے! \n", + "\n", + "🖱️ **آج ہی رابطہ کریں یا ہماری ویب سائٹ کا دورہ کریں!**\n", + "\n", + "\n", + "**نوٹ:** واقعی ویب سائٹ کے مخصوص روابط، ای میل اور نمبر تخلیقی مقصد کے لئے ہیں۔ اس کو حقیقی معلومات کے ساتھ تبدیل کیا جا سکتا ہے۔" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "multi_lingual_stream_brochure(\"OpenAI\", \"https://openai.com/\", \"Urdu\", \"humorous, entertaining, jokey\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b6f1e8d9", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4fb86dc6", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "llm_env", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} From 1c7c9e35e02b6322a9681f9fcf9b120235887cda Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:20:22 +1100 Subject: [PATCH 2/6] Day 5 Challend one with multilingual aloing with multitone --- .../day5-multi-lingual-desire-format.ipynb | 3112 +---------------- 1 file changed, 24 insertions(+), 3088 deletions(-) diff --git a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb index 3f1b3ad..b17c402 100644 --- a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb +++ b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb @@ -42,18 +42,10 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "API key looks good so far\n" - ] - } - ], + "outputs": [], "source": [ "# Initialize and constants\n", "\n", @@ -109,46 +101,10 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "id": "e30d8128-933b-44cc-81c8-ab4c9d86589a", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "['https://edwarddonner.com/',\n", - " 'https://edwarddonner.com/outsmart/',\n", - " 'https://edwarddonner.com/about-me-and-about-nebula/',\n", - " 'https://edwarddonner.com/posts/',\n", - " 'https://edwarddonner.com/',\n", - " 'https://news.ycombinator.com',\n", - " 'https://nebula.io/?utm_source=ed&utm_medium=referral',\n", - " 'https://www.prnewswire.com/news-releases/wynden-stark-group-acquires-nyc-venture-backed-tech-startup-untapt-301269512.html',\n", - " 'https://patents.google.com/patent/US20210049536A1/',\n", - " 'https://www.linkedin.com/in/eddonner/',\n", - " 'https://edwarddonner.com/2024/11/13/llm-engineering-resources/',\n", - " 'https://edwarddonner.com/2024/11/13/llm-engineering-resources/',\n", - " 'https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/',\n", - " 'https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/',\n", - " 'https://edwarddonner.com/2024/08/06/outsmart/',\n", - " 'https://edwarddonner.com/2024/08/06/outsmart/',\n", - " 'https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/',\n", - " 'https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/',\n", - " 'https://edwarddonner.com/',\n", - " 'https://edwarddonner.com/outsmart/',\n", - " 'https://edwarddonner.com/about-me-and-about-nebula/',\n", - " 'https://edwarddonner.com/posts/',\n", - " 'mailto:hello@mygroovydomain.com',\n", - " 'https://www.linkedin.com/in/eddonner/',\n", - " 'https://twitter.com/edwarddonner',\n", - " 'https://www.facebook.com/edward.donner.52']" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "ed = Website(\"https://edwarddonner.com\")\n", "ed.links" @@ -193,26 +149,10 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "id": "b97e4068-97ed-4120-beae-c42105e4d59a", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "You are provided with a list of links found on a webpage. You are able to decide which of the links would be most relevant to include in a brochure about the company, such as links to an About page, or a Company page, or Careers/Jobs pages.\n", - "You should respond in JSON as in this example:\n", - "{\n", - " \"links\": [\n", - " {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", - " {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", - " ]\n", - "}\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "print(link_system_prompt)" ] @@ -235,45 +175,10 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "id": "6bcbfa78-6395-4685-b92c-22d592050fd7", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Here is the list of links on the website of https://edwarddonner.com - please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. Do not include Terms of Service, Privacy, email links.\n", - "Links (some might be relative links):\n", - "https://edwarddonner.com/\n", - "https://edwarddonner.com/outsmart/\n", - "https://edwarddonner.com/about-me-and-about-nebula/\n", - "https://edwarddonner.com/posts/\n", - "https://edwarddonner.com/\n", - "https://news.ycombinator.com\n", - "https://nebula.io/?utm_source=ed&utm_medium=referral\n", - "https://www.prnewswire.com/news-releases/wynden-stark-group-acquires-nyc-venture-backed-tech-startup-untapt-301269512.html\n", - "https://patents.google.com/patent/US20210049536A1/\n", - "https://www.linkedin.com/in/eddonner/\n", - "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", - "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", - "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", - "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", - "https://edwarddonner.com/2024/08/06/outsmart/\n", - "https://edwarddonner.com/2024/08/06/outsmart/\n", - "https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/\n", - "https://edwarddonner.com/2024/06/26/choosing-the-right-llm-resources/\n", - "https://edwarddonner.com/\n", - "https://edwarddonner.com/outsmart/\n", - "https://edwarddonner.com/about-me-and-about-nebula/\n", - "https://edwarddonner.com/posts/\n", - "mailto:hello@mygroovydomain.com\n", - "https://www.linkedin.com/in/eddonner/\n", - "https://twitter.com/edwarddonner\n", - "https://www.facebook.com/edward.donner.52\n" - ] - } - ], + "outputs": [], "source": [ "print(get_links_user_prompt(ed))" ] @@ -301,100 +206,10 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "id": "74a827a0-2782-4ae5-b210-4a242a8b4cc2", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "['/',\n", - " '/models',\n", - " '/datasets',\n", - " '/spaces',\n", - " '/posts',\n", - " '/docs',\n", - " '/enterprise',\n", - " '/pricing',\n", - " '/login',\n", - " '/join',\n", - " '/IamCreateAI/Ruyi-Mini-7B',\n", - " '/Datou1111/shou_xin',\n", - " '/answerdotai/ModernBERT-base',\n", - " '/meta-llama/Llama-3.3-70B-Instruct',\n", - " '/tencent/HunyuanVideo',\n", - " '/models',\n", - " '/spaces/JeffreyXiang/TRELLIS',\n", - " '/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute',\n", - " '/spaces/multimodalart/flux-style-shaping',\n", - " '/spaces/Kwai-Kolors/Kolors-Virtual-Try-On',\n", - " '/spaces/lllyasviel/iclight-v2',\n", - " '/spaces',\n", - " '/datasets/fka/awesome-chatgpt-prompts',\n", - " '/datasets/O1-OPEN/OpenO1-SFT',\n", - " '/datasets/HuggingFaceFW/fineweb-2',\n", - " '/datasets/HuggingFaceTB/finemath',\n", - " '/datasets/amphora/QwQ-LongCoT-130K',\n", - " '/datasets',\n", - " '/join',\n", - " '/pricing#endpoints',\n", - " '/pricing#spaces',\n", - " '/pricing',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/enterprise',\n", - " '/allenai',\n", - " '/facebook',\n", - " '/amazon',\n", - " '/google',\n", - " '/Intel',\n", - " '/microsoft',\n", - " '/grammarly',\n", - " '/Writer',\n", - " '/docs/transformers',\n", - " '/docs/diffusers',\n", - " '/docs/safetensors',\n", - " '/docs/huggingface_hub',\n", - " '/docs/tokenizers',\n", - " '/docs/peft',\n", - " '/docs/transformers.js',\n", - " '/docs/timm',\n", - " '/docs/trl',\n", - " '/docs/datasets',\n", - " '/docs/text-generation-inference',\n", - " '/docs/accelerate',\n", - " '/models',\n", - " '/datasets',\n", - " '/spaces',\n", - " '/tasks',\n", - " 'https://ui.endpoints.huggingface.co',\n", - " '/chat',\n", - " '/huggingface',\n", - " '/brand',\n", - " '/terms-of-service',\n", - " '/privacy',\n", - " 'https://apply.workable.com/huggingface/',\n", - " 'mailto:press@huggingface.co',\n", - " '/learn',\n", - " '/docs',\n", - " '/blog',\n", - " 'https://discuss.huggingface.co',\n", - " 'https://status.huggingface.co/',\n", - " 'https://github.com/huggingface',\n", - " 'https://twitter.com/huggingface',\n", - " 'https://www.linkedin.com/company/huggingface/',\n", - " '/join/discord']" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# Anthropic has made their site harder to scrape, so I'm using HuggingFace..\n", "\n", @@ -404,28 +219,10 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "{'links': [{'type': 'homepage', 'url': 'https://huggingface.co/'},\n", - " {'type': 'about page', 'url': 'https://huggingface.co/huggingface'},\n", - " {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'},\n", - " {'type': 'blog', 'url': 'https://huggingface.co/blog'},\n", - " {'type': 'github page', 'url': 'https://github.com/huggingface'},\n", - " {'type': 'twitter page', 'url': 'https://twitter.com/huggingface'},\n", - " {'type': 'linkedin page',\n", - " 'url': 'https://www.linkedin.com/company/huggingface/'}]}" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "get_links(\"https://huggingface.co\")" ] @@ -460,2181 +257,10 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "id": "5099bd14-076d-4745-baf3-dac08d8e5ab2", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/about'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'company page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'community discussions', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n", - "Landing page:\n", - "Webpage Title:\n", - "Hugging Face – The AI community building the future.\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "The AI community building the future.\n", - "The platform where the machine learning community collaborates on models, datasets, and applications.\n", - "Trending on\n", - "this week\n", - "Models\n", - "IamCreateAI/Ruyi-Mini-7B\n", - "Updated\n", - "4 days ago\n", - "•\n", - "8.17k\n", - "•\n", - "352\n", - "Datou1111/shou_xin\n", - "Updated\n", - "12 days ago\n", - "•\n", - "28.3k\n", - "•\n", - "672\n", - "answerdotai/ModernBERT-base\n", - "Updated\n", - "1 day ago\n", - "•\n", - "6.24k\n", - "•\n", - "236\n", - "meta-llama/Llama-3.3-70B-Instruct\n", - "Updated\n", - "11 days ago\n", - "•\n", - "236k\n", - "•\n", - "1.21k\n", - "tencent/HunyuanVideo\n", - "Updated\n", - "3 days ago\n", - "•\n", - "6.01k\n", - "•\n", - "1.2k\n", - "Browse 400k+ models\n", - "Spaces\n", - "Running\n", - "on\n", - "Zero\n", - "1.79k\n", - "🏢\n", - "TRELLIS\n", - "Scalable and Versatile 3D Generation from images\n", - "Running\n", - "306\n", - "📝\n", - "Scaling test-time compute\n", - "Running\n", - "on\n", - "Zero\n", - "470\n", - "🚀\n", - "Flux Style Shaping\n", - "Optical illusions and style transfer with FLUX\n", - "Running\n", - "on\n", - "CPU Upgrade\n", - "6.11k\n", - "👕\n", - "Kolors Virtual Try-On\n", - "Running\n", - "on\n", - "Zero\n", - "965\n", - "📈\n", - "IC Light V2\n", - "Browse 150k+ applications\n", - "Datasets\n", - "fka/awesome-chatgpt-prompts\n", - "Updated\n", - "Sep 3\n", - "•\n", - "6.83k\n", - "•\n", - "6.58k\n", - "O1-OPEN/OpenO1-SFT\n", - "Updated\n", - "4 days ago\n", - "•\n", - "1.86k\n", - "•\n", - "234\n", - "HuggingFaceFW/fineweb-2\n", - "Updated\n", - "13 days ago\n", - "•\n", - "77.7k\n", - "•\n", - "342\n", - "HuggingFaceTB/finemath\n", - "Updated\n", - "1 day ago\n", - "•\n", - "1.86k\n", - "•\n", - "43\n", - "amphora/QwQ-LongCoT-130K\n", - "Updated\n", - "16 days ago\n", - "•\n", - "1.34k\n", - "•\n", - "85\n", - "Browse 100k+ datasets\n", - "The Home of Machine Learning\n", - "Create, discover and collaborate on ML better.\n", - "The collaboration platform\n", - "Host and collaborate on unlimited public models, datasets and applications.\n", - "Move faster\n", - "With the HF Open source stack.\n", - "Explore all modalities\n", - "Text, image, video, audio or even 3D.\n", - "Build your portfolio\n", - "Share your work with the world and build your ML profile.\n", - "Sign Up\n", - "Accelerate your ML\n", - "We provide paid Compute and Enterprise solutions.\n", - "Compute\n", - "Deploy on optimized\n", - "Inference Endpoints\n", - "or update your\n", - "Spaces applications\n", - "to a GPU in a few clicks.\n", - "View pricing\n", - "Starting at $0.60/hour for GPU\n", - "Enterprise\n", - "Give your team the most advanced platform to build AI with enterprise-grade security, access controls and\n", - "\t\t\tdedicated support.\n", - "Getting started\n", - "Starting at $20/user/month\n", - "Single Sign-On\n", - "Regions\n", - "Priority Support\n", - "Audit Logs\n", - "Resource Groups\n", - "Private Datasets Viewer\n", - "More than 50,000 organizations are using Hugging Face\n", - "Ai2\n", - "Enterprise\n", - "non-profit\n", - "•\n", - "366 models\n", - "•\n", - "1.76k followers\n", - "AI at Meta\n", - "Enterprise\n", - "company\n", - "•\n", - "2.05k models\n", - "•\n", - "3.83k followers\n", - "Amazon Web Services\n", - "company\n", - "•\n", - "21 models\n", - "•\n", - "2.45k followers\n", - "Google\n", - "company\n", - "•\n", - "911 models\n", - "•\n", - "5.76k followers\n", - "Intel\n", - "company\n", - "•\n", - "217 models\n", - "•\n", - "2.07k followers\n", - "Microsoft\n", - "company\n", - "•\n", - "351 models\n", - "•\n", - "6.29k followers\n", - "Grammarly\n", - "company\n", - "•\n", - "10 models\n", - "•\n", - "102 followers\n", - "Writer\n", - "Enterprise\n", - "company\n", - "•\n", - "17 models\n", - "•\n", - "186 followers\n", - "Our Open Source\n", - "We are building the foundation of ML tooling with the community.\n", - "Transformers\n", - "136,571\n", - "State-of-the-art ML for Pytorch, TensorFlow, and JAX.\n", - "Diffusers\n", - "26,740\n", - "State-of-the-art diffusion models for image and audio generation in PyTorch.\n", - "Safetensors\n", - "2,960\n", - "Simple, safe way to store and distribute neural networks weights safely and quickly.\n", - "Hub Python Library\n", - "2,177\n", - "Client library for the HF Hub: manage repositories from your Python runtime.\n", - "Tokenizers\n", - "9,165\n", - "Fast tokenizers, optimized for both research and production.\n", - "PEFT\n", - "16,767\n", - "Parameter efficient finetuning methods for large models.\n", - "Transformers.js\n", - "12,421\n", - "State-of-the-art Machine Learning for the web. Run Transformers directly in your browser, with no need for a server.\n", - "timm\n", - "32,668\n", - "State-of-the-art computer vision models, layers, optimizers, training/evaluation, and utilities.\n", - "TRL\n", - "10,382\n", - "Train transformer language models with reinforcement learning.\n", - "Datasets\n", - "19,378\n", - "Access and share datasets for computer vision, audio, and NLP tasks.\n", - "Text Generation Inference\n", - "9,484\n", - "Toolkit to serve Large Language Models.\n", - "Accelerate\n", - "8,082\n", - "Easily train and use PyTorch models with multi-GPU, TPU, mixed-precision.\n", - "System theme\n", - "Website\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Tasks\n", - "Inference Endpoints\n", - "HuggingChat\n", - "Company\n", - "About\n", - "Brand assets\n", - "Terms of service\n", - "Privacy\n", - "Jobs\n", - "Press\n", - "Resources\n", - "Learn\n", - "Documentation\n", - "Blog\n", - "Forum\n", - "Service Status\n", - "Social\n", - "GitHub\n", - "Twitter\n", - "LinkedIn\n", - "Discord\n", - "\n", - "\n", - "\n", - "about page\n", - "Webpage Title:\n", - "about (Sergei)\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "Sergei\n", - "about\n", - "Follow\n", - "Kalaipriya's profile picture\n", - "selvivincent's profile picture\n", - "Renumathi's profile picture\n", - "3\n", - "\t\t\t\t\tfollowers\n", - "·\n", - "0 following\n", - "AI & ML interests\n", - "None yet\n", - "Organizations\n", - "None yet\n", - "models\n", - "None public yet\n", - "datasets\n", - "None public yet\n", - "System theme\n", - "Company\n", - "TOS\n", - "Privacy\n", - "About\n", - "Jobs\n", - "Website\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Pricing\n", - "Docs\n", - "\n", - "\n", - "\n", - "careers page\n", - "Webpage Title:\n", - "Hugging Face - Current Openings\n", - "Webpage Contents:\n", - "\n", - "\n", - "\n", - "\n", - "blog page\n", - "Webpage Title:\n", - "Hugging Face – Blog\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "Blog, Articles, and discussions\n", - "New Article\n", - "Everything\n", - "community\n", - "guide\n", - "open source collab\n", - "partnerships\n", - "research\n", - "NLP\n", - "Audio\n", - "CV\n", - "RL\n", - "ethics\n", - "Diffusion\n", - "Game Development\n", - "RLHF\n", - "Leaderboard\n", - "Case Studies\n", - "Evaluating Audio Reasoning with Big Bench Audio\n", - "By\n", - "mhillsmith\n", - "December 20, 2024\n", - "guest\n", - "•\n", - "8\n", - "Community Articles\n", - "view all\n", - "20+ Free and Paid Digital Marketing Strategies to Automate Repetitive Tasks\n", - "By\n", - "Markets\n", - "•\n", - "about 3 hours ago\n", - "•\n", - "1\n", - "🧠 Tags generation dataset\n", - "By\n", - "zino36\n", - "•\n", - "about 16 hours ago\n", - "•\n", - "1\n", - "AI Agents in Action: Managing GitHub Issues with KaibanJS\n", - "By\n", - "darielnoel\n", - "•\n", - "1 day ago\n", - "**Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs**\n", - "By\n", - "KnutJaegersberg\n", - "•\n", - "1 day ago\n", - "•\n", - "3\n", - "MINERVA: A Multi-Agent LLM System for Digital Scam Protection\n", - "By\n", - "dcarpintero\n", - "•\n", - "2 days ago\n", - "Mastering Iterative Prompting for Optimized AI Code Generation\n", - "By\n", - "luigi12345\n", - "•\n", - "3 days ago\n", - "•\n", - "1\n", - "SILMA RAGQA V1.0: A Comprehensive Benchmark for Evaluating LLMs on RAG QA Use-Cases\n", - "By\n", - "karimouda\n", - "•\n", - "3 days ago\n", - "•\n", - "1\n", - "FuseChat-3.0: Preference Optimization for Implicit Model Fusion\n", - "By\n", - "Wanfq\n", - "•\n", - "3 days ago\n", - "•\n", - "2\n", - "Tutorial: Quantizing Llama 3+ Models for Efficient Deployment\n", - "By\n", - "theeseus-ai\n", - "•\n", - "6 days ago\n", - "•\n", - "3\n", - "How to Expand Your AI Music Generations of 30 Seconds to Several Minutes\n", - "By\n", - "theeseus-ai\n", - "•\n", - "8 days ago\n", - "•\n", - "1\n", - "🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺\n", - "By\n", - "yjernite\n", - "•\n", - "9 days ago\n", - "•\n", - "11\n", - "Building an AI-powered search engine from scratch\n", - "By\n", - "as-cle-bert\n", - "•\n", - "10 days ago\n", - "•\n", - "8\n", - "MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion\n", - "By\n", - "wxDai\n", - "•\n", - "10 days ago\n", - "•\n", - "12\n", - "RLHF 101: A Technical Dive into RLHF\n", - "By\n", - "GitBag\n", - "•\n", - "10 days ago\n", - "•\n", - "4\n", - "[Talk Arena](https://talkarena.org)\n", - "By\n", - "WillHeld\n", - "•\n", - "11 days ago\n", - "•\n", - "1\n", - "Multimodal RAG with Colpali, Milvus and VLMs\n", - "By\n", - "saumitras\n", - "•\n", - "11 days ago\n", - "•\n", - "2\n", - "In Honour of This Year's NeurIPs Test of Time Paper Awardees\n", - "By\n", - "Jaward\n", - "•\n", - "11 days ago\n", - "•\n", - "2\n", - "Power steering: Squeeze massive power from small LLMs\n", - "By\n", - "ucheog\n", - "•\n", - "12 days ago\n", - "•\n", - "4\n", - "Exploring the Power of KaibanJS v0.11.0 🚀\n", - "By\n", - "darielnoel\n", - "•\n", - "12 days ago\n", - "•\n", - "1\n", - "**Building a Custom Retrieval System with Motoko and Node.js**\n", - "By\n", - "theeseus-ai\n", - "•\n", - "12 days ago\n", - "•\n", - "1\n", - "Finally, a Replacement for BERT: Introducing ModernBERT\n", - "By\n", - "bwarner\n", - "December 19, 2024\n", - "guest\n", - "•\n", - "289\n", - "Bamba: Inference-Efficient Hybrid Mamba2 Model\n", - "By\n", - "Linsong-C\n", - "December 18, 2024\n", - "guest\n", - "•\n", - "30\n", - "Welcome the Falcon 3 Family of Open Models!\n", - "By\n", - "FalconLLM\n", - "December 17, 2024\n", - "•\n", - "98\n", - "Benchmarking Language Model Performance on 5th Gen Xeon at GCP\n", - "By\n", - "MatrixYao\n", - "December 17, 2024\n", - "•\n", - "2\n", - "Introducing the Synthetic Data Generator - Build Datasets with Natural Language\n", - "By\n", - "davidberenstein1957\n", - "December 16, 2024\n", - "•\n", - "55\n", - "LeMaterial: an open source initiative to accelerate materials discovery and research\n", - "By\n", - "AlexDuvalinho\n", - "December 10, 2024\n", - "guest\n", - "•\n", - "30\n", - "Hugging Face models in Amazon Bedrock\n", - "By\n", - "pagezyhf\n", - "December 9, 2024\n", - "•\n", - "8\n", - "Open Preference Dataset for Text-to-Image Generation by the 🤗 Community\n", - "By\n", - "davidberenstein1957\n", - "December 9, 2024\n", - "•\n", - "47\n", - "Welcome PaliGemma 2 – New vision language models by Google\n", - "By\n", - "merve\n", - "December 5, 2024\n", - "•\n", - "117\n", - "“How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs\n", - "By\n", - "martin-gorner\n", - "December 5, 2024\n", - "•\n", - "12\n", - "Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard\n", - "By\n", - "alielfilali01\n", - "December 4, 2024\n", - "guest\n", - "•\n", - "26\n", - "Investing in Performance: Fine-tune small models with LLM insights - a CFM case study\n", - "By\n", - "oahouzi\n", - "December 3, 2024\n", - "•\n", - "25\n", - "Rearchitecting Hugging Face Uploads and Downloads\n", - "By\n", - "port8080\n", - "November 26, 2024\n", - "•\n", - "37\n", - "SmolVLM - small yet mighty Vision Language Model\n", - "By\n", - "andito\n", - "November 26, 2024\n", - "•\n", - "142\n", - "Previous\n", - "1\n", - "2\n", - "3\n", - "...\n", - "36\n", - "Next\n", - "Community Articles\n", - "view all\n", - "20+ Free and Paid Digital Marketing Strategies to Automate Repetitive Tasks\n", - "By\n", - "Markets\n", - "•\n", - "about 3 hours ago\n", - "•\n", - "1\n", - "🧠 Tags generation dataset\n", - "By\n", - "zino36\n", - "•\n", - "about 16 hours ago\n", - "•\n", - "1\n", - "AI Agents in Action: Managing GitHub Issues with KaibanJS\n", - "By\n", - "darielnoel\n", - "•\n", - "1 day ago\n", - "**Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs**\n", - "By\n", - "KnutJaegersberg\n", - "•\n", - "1 day ago\n", - "•\n", - "3\n", - "MINERVA: A Multi-Agent LLM System for Digital Scam Protection\n", - "By\n", - "dcarpintero\n", - "•\n", - "2 days ago\n", - "Mastering Iterative Prompting for Optimized AI Code Generation\n", - "By\n", - "luigi12345\n", - "•\n", - "3 days ago\n", - "•\n", - "1\n", - "SILMA RAGQA V1.0: A Comprehensive Benchmark for Evaluating LLMs on RAG QA Use-Cases\n", - "By\n", - "karimouda\n", - "•\n", - "3 days ago\n", - "•\n", - "1\n", - "FuseChat-3.0: Preference Optimization for Implicit Model Fusion\n", - "By\n", - "Wanfq\n", - "•\n", - "3 days ago\n", - "•\n", - "2\n", - "Tutorial: Quantizing Llama 3+ Models for Efficient Deployment\n", - "By\n", - "theeseus-ai\n", - "•\n", - "6 days ago\n", - "•\n", - "3\n", - "How to Expand Your AI Music Generations of 30 Seconds to Several Minutes\n", - "By\n", - "theeseus-ai\n", - "•\n", - "8 days ago\n", - "•\n", - "1\n", - "🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺\n", - "By\n", - "yjernite\n", - "•\n", - "9 days ago\n", - "•\n", - "11\n", - "Building an AI-powered search engine from scratch\n", - "By\n", - "as-cle-bert\n", - "•\n", - "10 days ago\n", - "•\n", - "8\n", - "MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion\n", - "By\n", - "wxDai\n", - "•\n", - "10 days ago\n", - "•\n", - "12\n", - "RLHF 101: A Technical Dive into RLHF\n", - "By\n", - "GitBag\n", - "•\n", - "10 days ago\n", - "•\n", - "4\n", - "[Talk Arena](https://talkarena.org)\n", - "By\n", - "WillHeld\n", - "•\n", - "11 days ago\n", - "•\n", - "1\n", - "Multimodal RAG with Colpali, Milvus and VLMs\n", - "By\n", - "saumitras\n", - "•\n", - "11 days ago\n", - "•\n", - "2\n", - "In Honour of This Year's NeurIPs Test of Time Paper Awardees\n", - "By\n", - "Jaward\n", - "•\n", - "11 days ago\n", - "•\n", - "2\n", - "Power steering: Squeeze massive power from small LLMs\n", - "By\n", - "ucheog\n", - "•\n", - "12 days ago\n", - "•\n", - "4\n", - "Exploring the Power of KaibanJS v0.11.0 🚀\n", - "By\n", - "darielnoel\n", - "•\n", - "12 days ago\n", - "•\n", - "1\n", - "**Building a Custom Retrieval System with Motoko and Node.js**\n", - "By\n", - "theeseus-ai\n", - "•\n", - "12 days ago\n", - "•\n", - "1\n", - "System theme\n", - "Company\n", - "TOS\n", - "Privacy\n", - "About\n", - "Jobs\n", - "Website\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Pricing\n", - "Docs\n", - "\n", - "\n", - "\n", - "company page\n", - "Webpage Title:\n", - "huggingface (Hugging Face)\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "Hugging Face\n", - "Enterprise\n", - "company\n", - "Verified\n", - "https://huggingface.co\n", - "huggingface\n", - "huggingface\n", - "Activity Feed\n", - "Follow\n", - "8,542\n", - "AI & ML interests\n", - "The AI community building the future.\n", - "Recent Activity\n", - "IAMJB\n", - "updated\n", - "a dataset\n", - "9 minutes ago\n", - "huggingface/community-science-paper-v2\n", - "IAMJB\n", - "updated\n", - "a dataset\n", - "about 6 hours ago\n", - "huggingface/paper-central-data\n", - "fdaudens\n", - "updated\n", - "a Space\n", - "about 19 hours ago\n", - "huggingface/open-source-ai-year-in-review-2024\n", - "View all activity\n", - "Team members\n", - "224\n", - "+190\n", - "+177\n", - "+156\n", - "+146\n", - "+126\n", - "Organization Card\n", - "Community\n", - "About org cards\n", - "👋 Hi!\n", - "We are on a mission to democratize\n", - "good\n", - "machine learning, one commit at a time.\n", - "If that sounds like something you should be doing, why don't you\n", - "join us\n", - "!\n", - "For press enquiries, you can\n", - "✉️ contact our team here\n", - ".\n", - "Collections\n", - "1\n", - "DistilBERT release\n", - "Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.\n", - "distilbert/distilbert-base-cased\n", - "Fill-Mask\n", - "•\n", - "Updated\n", - "May 6\n", - "•\n", - "358k\n", - "•\n", - "35\n", - "distilbert/distilbert-base-uncased\n", - "Fill-Mask\n", - "•\n", - "Updated\n", - "May 6\n", - "•\n", - "14.8M\n", - "•\n", - "577\n", - "distilbert/distilbert-base-multilingual-cased\n", - "Fill-Mask\n", - "•\n", - "Updated\n", - "May 6\n", - "•\n", - "472k\n", - "•\n", - "148\n", - "distilbert/distilbert-base-uncased-finetuned-sst-2-english\n", - "Text Classification\n", - "•\n", - "Updated\n", - "Dec 19, 2023\n", - "•\n", - "6.96M\n", - "•\n", - "•\n", - "645\n", - "spaces\n", - "23\n", - "Sort: \n", - "\t\tRecently updated\n", - "pinned\n", - "Running\n", - "52\n", - "📈\n", - "Number Tokenization Blog\n", - "Running\n", - "395\n", - "😻\n", - "Open Source Ai Year In Review 2024\n", - "What happened in open-source AI this year, and what’s next?\n", - "Running\n", - "42\n", - "🔋\n", - "Inference Playground\n", - "Running\n", - "196\n", - "⚡\n", - "paper-central\n", - "Running\n", - "on\n", - "TPU v5e\n", - "6\n", - "💬\n", - "Keras Chatbot Battle\n", - "Running\n", - "101\n", - "⚡\n", - "Modelcard Creator\n", - "Expand 23\n", - "\t\t\t\t\t\t\tspaces\n", - "models\n", - "18\n", - "Sort: \n", - "\t\tRecently updated\n", - "huggingface/test-gating-group-2\n", - "Updated\n", - "4 days ago\n", - "huggingface/test-gating-group-1\n", - "Updated\n", - "4 days ago\n", - "huggingface/timesfm-tourism-monthly\n", - "Updated\n", - "12 days ago\n", - "•\n", - "29\n", - "•\n", - "1\n", - "huggingface/CodeBERTa-language-id\n", - "Text Classification\n", - "•\n", - "Updated\n", - "Mar 29\n", - "•\n", - "1.14k\n", - "•\n", - "54\n", - "huggingface/falcon-40b-gptq\n", - "Text Generation\n", - "•\n", - "Updated\n", - "Jun 14, 2023\n", - "•\n", - "19\n", - "•\n", - "12\n", - "huggingface/autoformer-tourism-monthly\n", - "Updated\n", - "May 24, 2023\n", - "•\n", - "1.5k\n", - "•\n", - "9\n", - "huggingface/distilbert-base-uncased-finetuned-mnli\n", - "Text Classification\n", - "•\n", - "Updated\n", - "Mar 22, 2023\n", - "•\n", - "1.37k\n", - "•\n", - "2\n", - "huggingface/informer-tourism-monthly\n", - "Updated\n", - "Feb 24, 2023\n", - "•\n", - "1.12k\n", - "•\n", - "5\n", - "huggingface/time-series-transformer-tourism-monthly\n", - "Updated\n", - "Feb 23, 2023\n", - "•\n", - "2.16k\n", - "•\n", - "18\n", - "huggingface/the-no-branch-repo\n", - "Text-to-Image\n", - "•\n", - "Updated\n", - "Feb 10, 2023\n", - "•\n", - "7\n", - "•\n", - "3\n", - "Expand 18\n", - "\t\t\t\t\t\t\tmodels\n", - "datasets\n", - "31\n", - "Sort: \n", - "\t\tRecently updated\n", - "huggingface/community-science-paper-v2\n", - "Viewer\n", - "•\n", - "Updated\n", - "9 minutes ago\n", - "•\n", - "5.03k\n", - "•\n", - "404\n", - "•\n", - "7\n", - "huggingface/paper-central-data\n", - "Viewer\n", - "•\n", - "Updated\n", - "about 6 hours ago\n", - "•\n", - "119k\n", - "•\n", - "553\n", - "•\n", - "8\n", - "huggingface/documentation-images\n", - "Viewer\n", - "•\n", - "Updated\n", - "1 day ago\n", - "•\n", - "44\n", - "•\n", - "2.43M\n", - "•\n", - "43\n", - "huggingface/transformers-metadata\n", - "Viewer\n", - "•\n", - "Updated\n", - "2 days ago\n", - "•\n", - "1.52k\n", - "•\n", - "559\n", - "•\n", - "14\n", - "huggingface/diffusers-metadata\n", - "Viewer\n", - "•\n", - "Updated\n", - "2 days ago\n", - "•\n", - "62\n", - "•\n", - "442\n", - "•\n", - "4\n", - "huggingface/policy-docs\n", - "Updated\n", - "3 days ago\n", - "•\n", - "898\n", - "•\n", - "6\n", - "huggingface/my-distiset-3f5a230e\n", - "Updated\n", - "30 days ago\n", - "•\n", - "17\n", - "huggingface/cookbook-images\n", - "Viewer\n", - "•\n", - "Updated\n", - "Nov 14\n", - "•\n", - "1\n", - "•\n", - "40.1k\n", - "•\n", - "6\n", - "huggingface/vllm-metadata\n", - "Updated\n", - "Oct 8\n", - "•\n", - "12\n", - "huggingface/paper-central-data-2\n", - "Viewer\n", - "•\n", - "Updated\n", - "Oct 4\n", - "•\n", - "58.3k\n", - "•\n", - "68\n", - "•\n", - "2\n", - "Expand 31\n", - "\t\t\t\t\t\t\tdatasets\n", - "System theme\n", - "Company\n", - "TOS\n", - "Privacy\n", - "About\n", - "Jobs\n", - "Website\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Pricing\n", - "Docs\n", - "\n", - "\n", - "\n", - "community discussions\n", - "Webpage Title:\n", - "Hugging Face Forums - Hugging Face Community Discussion\n", - "Webpage Contents:\n", - "Loading\n", - "Hugging Face Forums\n", - "Topic\n", - "Replies\n", - "Views\n", - "Activity\n", - "List of `size_categories`\n", - "🤗Datasets\n", - "3\n", - "5\n", - "December 21, 2024\n", - "Feature request - maintain list of favorite hf pages reachable from my hom epage\n", - "Site Feedback\n", - "4\n", - "886\n", - "December 21, 2024\n", - "404 error on carbon emission calculation\n", - "Site Feedback\n", - "1\n", - "7\n", - "December 21, 2024\n", - "Cannot connect gRPC Server Hosted on HuggingFace Spaces\n", - "Spaces\n", - "0\n", - "8\n", - "December 21, 2024\n", - "Hide system prompt or system instruction\n", - "Beginners\n", - "3\n", - "15\n", - "December 21, 2024\n", - "ModuleNotFoundError: No module named 'huggingface_hub.inference._types'\n", - "🤗Hub\n", - "0\n", - "5\n", - "December 21, 2024\n", - "Understanding State Management with Gradio and LangGraph\n", - "Beginners\n", - "1\n", - "11\n", - "December 21, 2024\n", - "Dimension problem\n", - "Beginners\n", - "25\n", - "21\n", - "December 21, 2024\n", - "Fine-tuning whisper on sound-event-detection dataset\n", - "🤗Transformers\n", - "0\n", - "4\n", - "December 20, 2024\n", - "Model that can generate both text and image as output\n", - "Research\n", - "4\n", - "42\n", - "December 21, 2024\n", - "Lm studio and Chat ui doesn't work with module\n", - "Beginners\n", - "11\n", - "33\n", - "December 21, 2024\n", - "Inference API Context Window and TOS\n", - "Beginners\n", - "0\n", - "12\n", - "December 20, 2024\n", - "Talkie AI got remove from app store -any alternative ai chat?\n", - "Beginners\n", - "4\n", - "1151\n", - "December 18, 2024\n", - "Inference Text Generation API issue\n", - "Intermediate\n", - "0\n", - "7\n", - "December 20, 2024\n", - "From Pandas Dataframe to Huggingface Dataset\n", - "Beginners\n", - "9\n", - "60459\n", - "December 20, 2024\n", - "\"Load Diffusion Model\" and \"Unet Loader (GGUF)\" null/undefined\n", - "Beginners\n", - "6\n", - "200\n", - "December 20, 2024\n", - "Timeout Issue with DeepSpeed on Multiple GPUs\n", - "DeepSpeed\n", - "0\n", - "8\n", - "December 20, 2024\n", - "Spaces dedicated gpu limit\n", - "Spaces\n", - "1\n", - "14\n", - "December 19, 2024\n", - "Chatbot PDF - using flan-t5-large model\n", - "Models\n", - "0\n", - "7\n", - "December 20, 2024\n", - "Gateway Problem\n", - "Beginners\n", - "0\n", - "8\n", - "December 20, 2024\n", - "RT-DETR attention map dimension - PekingU/rtdetr_r50vd\n", - "Models\n", - "0\n", - "5\n", - "December 20, 2024\n", - "Extending the tokenizer affects model generation\n", - "Intermediate\n", - "3\n", - "9\n", - "December 19, 2024\n", - "How to Ensure Each Process Reads Its Own Dataset and Trains Correctly When Using Trainer?\n", - "🤗Transformers\n", - "0\n", - "5\n", - "December 20, 2024\n", - "Can't save the tensorflow model of nvidia/mit-b5\n", - "Intermediate\n", - "3\n", - "127\n", - "December 19, 2024\n", - "# Audio course Unit 4. sample code not working. Can anyone check for me? Thanks\n", - "Course\n", - "0\n", - "6\n", - "December 20, 2024\n", - "Host Models on Hugging face and Perform Inference on Hugging Face Infrastructure\n", - "Beginners\n", - "0\n", - "6\n", - "December 20, 2024\n", - "Torchrun, trainer, dataset setup\n", - "Intermediate\n", - "4\n", - "71\n", - "December 20, 2024\n", - "Training fails on multiple GPUs with RuntimeError 'chuck expects at least a 1-dimensional array'\n", - "Beginners\n", - "2\n", - "108\n", - "December 19, 2024\n", - "How do you know whether the model is merged and uploaded?\n", - "Intermediate\n", - "0\n", - "11\n", - "December 20, 2024\n", - "Qwen based AI assistant randomly having an absolute, utter, complete 'mental breakdowns'?? (Inference API)\n", - "🤗Transformers\n", - "2\n", - "23\n", - "December 17, 2024\n", - "next page →\n", - "Home\n", - "Categories\n", - "Guidelines\n", - "Terms of Service\n", - "Privacy Policy\n", - "Powered by\n", - "Discourse\n", - ", best viewed with JavaScript enabled\n", - "\n", - "\n", - "\n", - "GitHub page\n", - "Webpage Title:\n", - "Hugging Face · GitHub\n", - "Webpage Contents:\n", - "Skip to content\n", - "Navigation Menu\n", - "Toggle navigation\n", - "Sign in\n", - "huggingface\n", - "Product\n", - "GitHub Copilot\n", - "Write better code with AI\n", - "Security\n", - "Find and fix vulnerabilities\n", - "Actions\n", - "Automate any workflow\n", - "Codespaces\n", - "Instant dev environments\n", - "Issues\n", - "Plan and track work\n", - "Code Review\n", - "Manage code changes\n", - "Discussions\n", - "Collaborate outside of code\n", - "Code Search\n", - "Find more, search less\n", - "Explore\n", - "All features\n", - "Documentation\n", - "GitHub Skills\n", - "Blog\n", - "Solutions\n", - "By company size\n", - "Enterprises\n", - "Small and medium teams\n", - "Startups\n", - "By use case\n", - "DevSecOps\n", - "DevOps\n", - "CI/CD\n", - "View all use cases\n", - "By industry\n", - "Healthcare\n", - "Financial services\n", - "Manufacturing\n", - "Government\n", - "View all industries\n", - "View all solutions\n", - "Resources\n", - "Topics\n", - "AI\n", - "DevOps\n", - "Security\n", - "Software Development\n", - "View all\n", - "Explore\n", - "Learning Pathways\n", - "White papers, Ebooks, Webinars\n", - "Customer Stories\n", - "Partners\n", - "Executive Insights\n", - "Open Source\n", - "GitHub Sponsors\n", - "Fund open source developers\n", - "The ReadME Project\n", - "GitHub community articles\n", - "Repositories\n", - "Topics\n", - "Trending\n", - "Collections\n", - "Enterprise\n", - "Enterprise platform\n", - "AI-powered developer platform\n", - "Available add-ons\n", - "Advanced Security\n", - "Enterprise-grade security features\n", - "GitHub Copilot\n", - "Enterprise-grade AI features\n", - "Premium Support\n", - "Enterprise-grade 24/7 support\n", - "Pricing\n", - "Search or jump to...\n", - "Search code, repositories, users, issues, pull requests...\n", - "Search\n", - "Clear\n", - "Search syntax tips\n", - "Provide feedback\n", - "We read every piece of feedback, and take your input very seriously.\n", - "Include my email address so I can be contacted\n", - "Cancel\n", - "Submit feedback\n", - "Saved searches\n", - "Use saved searches to filter your results more quickly\n", - "Cancel\n", - "Create saved search\n", - "Sign in\n", - "Sign up\n", - "Reseting focus\n", - "You signed in with another tab or window.\n", - "Reload\n", - "to refresh your session.\n", - "You signed out in another tab or window.\n", - "Reload\n", - "to refresh your session.\n", - "You switched accounts on another tab or window.\n", - "Reload\n", - "to refresh your session.\n", - "Dismiss alert\n", - "Hugging Face\n", - "The AI community building the future.\n", - "Verified\n", - "We've verified that the organization\n", - "huggingface\n", - "controls the domain:\n", - "huggingface.co\n", - "Learn more about verified organizations\n", - "40.1k\n", - "followers\n", - "NYC + Paris\n", - "https://huggingface.co/\n", - "X\n", - "@huggingface\n", - "Overview\n", - "Repositories\n", - "Projects\n", - "Packages\n", - "People\n", - "Sponsoring\n", - "0\n", - "More\n", - "Overview\n", - "Repositories\n", - "Projects\n", - "Packages\n", - "People\n", - "Sponsoring\n", - "Pinned\n", - "Loading\n", - "transformers\n", - "transformers\n", - "Public\n", - "🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.\n", - "Python\n", - "137k\n", - "27.3k\n", - "diffusers\n", - "diffusers\n", - "Public\n", - "🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.\n", - "Python\n", - "26.7k\n", - "5.5k\n", - "datasets\n", - "datasets\n", - "Public\n", - "🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools\n", - "Python\n", - "19.4k\n", - "2.7k\n", - "peft\n", - "peft\n", - "Public\n", - "🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.\n", - "Python\n", - "16.8k\n", - "1.7k\n", - "accelerate\n", - "accelerate\n", - "Public\n", - "🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support\n", - "Python\n", - "8.1k\n", - "995\n", - "optimum\n", - "optimum\n", - "Public\n", - "🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools\n", - "Python\n", - "2.6k\n", - "486\n", - "Repositories\n", - "Loading\n", - "Type\n", - "Select type\n", - "Forks\n", - "Archived\n", - "Mirrors\n", - "Templates\n", - "Language\n", - "Select language\n", - "All\n", - "C\n", - "C#\n", - "C++\n", - "Cuda\n", - "Dockerfile\n", - "Go\n", - "Handlebars\n", - "HTML\n", - "Java\n", - "JavaScript\n", - "Jupyter Notebook\n", - "Kotlin\n", - "Lua\n", - "MDX\n", - "Mustache\n", - "Nix\n", - "Python\n", - "Rust\n", - "Shell\n", - "Smarty\n", - "Swift\n", - "TypeScript\n", - "Sort\n", - "Select order\n", - "Last updated\n", - "Name\n", - "Stars\n", - "Showing 10 of 275 repositories\n", - "trl\n", - "Public\n", - "Train transformer language models with reinforcement learning.\n", - "huggingface/trl’s past year of commit activity\n", - "Python\n", - "10,382\n", - "Apache-2.0\n", - "1,337\n", - "106\n", - "46\n", - "Updated\n", - "Dec 21, 2024\n", - "transformers.js\n", - "Public\n", - "State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!\n", - "huggingface/transformers.js’s past year of commit activity\n", - "JavaScript\n", - "12,421\n", - "Apache-2.0\n", - "790\n", - "274\n", - "(3 issues need help)\n", - "48\n", - "Updated\n", - "Dec 21, 2024\n", - "diffusers\n", - "Public\n", - "🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.\n", - "huggingface/diffusers’s past year of commit activity\n", - "Python\n", - "26,740\n", - "Apache-2.0\n", - "5,504\n", - "379\n", - "(10 issues need help)\n", - "169\n", - "Updated\n", - "Dec 21, 2024\n", - "text-generation-inference\n", - "Public\n", - "Large Language Model Text Generation Inference\n", - "huggingface/text-generation-inference’s past year of commit activity\n", - "Python\n", - "9,484\n", - "Apache-2.0\n", - "1,106\n", - "152\n", - "21\n", - "Updated\n", - "Dec 21, 2024\n", - "candle\n", - "Public\n", - "Minimalist ML framework for Rust\n", - "huggingface/candle’s past year of commit activity\n", - "Rust\n", - "16,103\n", - "Apache-2.0\n", - "980\n", - "344\n", - "(5 issues need help)\n", - "86\n", - "Updated\n", - "Dec 21, 2024\n", - "autotrain-advanced\n", - "Public\n", - "🤗 AutoTrain Advanced\n", - "huggingface/autotrain-advanced’s past year of commit activity\n", - "Python\n", - "4,157\n", - "Apache-2.0\n", - "505\n", - "16\n", - "2\n", - "Updated\n", - "Dec 21, 2024\n", - "transformers\n", - "Public\n", - "🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.\n", - "huggingface/transformers’s past year of commit activity\n", - "Python\n", - "136,571\n", - "Apache-2.0\n", - "27,342\n", - "1,003\n", - "(2 issues need help)\n", - "526\n", - "Updated\n", - "Dec 21, 2024\n", - "lighteval\n", - "Public\n", - "Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends\n", - "huggingface/lighteval’s past year of commit activity\n", - "Python\n", - "889\n", - "MIT\n", - "109\n", - "62\n", - "(1 issue needs help)\n", - "15\n", - "Updated\n", - "Dec 21, 2024\n", - "hub-docs\n", - "Public\n", - "Docs of the Hugging Face Hub\n", - "huggingface/hub-docs’s past year of commit activity\n", - "Handlebars\n", - "309\n", - "Apache-2.0\n", - "259\n", - "90\n", - "25\n", - "Updated\n", - "Dec 21, 2024\n", - "optimum-habana\n", - "Public\n", - "Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)\n", - "huggingface/optimum-habana’s past year of commit activity\n", - "Python\n", - "162\n", - "Apache-2.0\n", - "219\n", - "11\n", - "(1 issue needs help)\n", - "40\n", - "Updated\n", - "Dec 21, 2024\n", - "View all repositories\n", - "People\n", - "View all\n", - "Top languages\n", - "Python\n", - "Jupyter Notebook\n", - "Rust\n", - "TypeScript\n", - "JavaScript\n", - "Most used topics\n", - "pytorch\n", - "machine-learning\n", - "nlp\n", - "deep-learning\n", - "transformers\n", - "Footer\n", - "© 2024 GitHub, Inc.\n", - "Footer navigation\n", - "Terms\n", - "Privacy\n", - "Security\n", - "Status\n", - "Docs\n", - "Contact\n", - "Manage cookies\n", - "Do not share my personal information\n", - "You can’t perform that action at this time.\n", - "\n", - "\n", - "\n", - "Twitter page\n", - "Webpage Title:\n", - "x.com\n", - "Webpage Contents:\n", - "\n", - "\n", - "\n", - "\n", - "LinkedIn page\n", - "Webpage Title:\n", - "Hugging Face | LinkedIn\n", - "Webpage Contents:\n", - "Skip to main content\n", - "LinkedIn\n", - "Articles\n", - "People\n", - "Learning\n", - "Jobs\n", - "Games\n", - "Get the app\n", - "Join now\n", - "Sign in\n", - "Hugging Face\n", - "Software Development\n", - "The AI community building the future.\n", - "See jobs\n", - "Follow\n", - "Discover all 472 employees\n", - "Report this company\n", - "About us\n", - "The AI community building the future.\n", - "Website\n", - "https://huggingface.co\n", - "External link for Hugging Face\n", - "Industry\n", - "Software Development\n", - "Company size\n", - "51-200 employees\n", - "Type\n", - "Privately Held\n", - "Founded\n", - "2016\n", - "Specialties\n", - "machine learning, natural language processing, and deep learning\n", - "Products\n", - "Hugging Face\n", - "Hugging Face\n", - "Natural Language Processing (NLP) Software\n", - "We‚Äôre on a journey to solve and democratize artificial intelligence through natural language.\n", - "Locations\n", - "Primary\n", - "Get directions\n", - "Paris, FR\n", - "Get directions\n", - "Employees at Hugging Face\n", - "Ludovic Huraux\n", - "Bassem ASSEH\n", - "Rajat Arya\n", - "Tech Lead & Software Engineer @ HF | prev: co-founder XetHub, Apple, Turi, AWS, Microsoft\n", - "Jeff Boudier\n", - "Product + Growth at Hugging Face\n", - "See all employees\n", - "Updates\n", - "Hugging Face\n", - "reposted this\n", - "Gradio\n", - "47,326 followers\n", - "7h\n", - "Report this post\n", - "NOW you can add AI to your Slack, Discord in just few steps with Gradio!ü§©\n", - "\n", - "üî•Create Slack apps, Discord bots, or Intercom-style website widgets in ANY modality (Text, image, Video, Audio, Omni etc)! Keep reading to learn how ‚¨áÔ∏è\n", - "\n", - "Guide: üöÄ Creating a Slack Bot from a Gradio App üöÄ\n", - "Read here:\n", - "https://lnkd.in/g2_Bydrj\n", - "ü§éDo you love building stuff with Gradio? Support us on GitHub:\n", - "Gradio.dev\n", - "‚Ķmore\n", - "50\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Daniel V.\n", - "Machine Learning Librarian@ü§ó | Championing Open Science & Machine Learning\n", - "21h\n", - "Report this post\n", - "Introducing FineWeb-C üåêüéì, a community-built dataset for improving language models in ALL languages. \n", - "\n", - "Inspired by FineWeb-Edu the community is labelling the educational quality of texts for many languages. \n", - "\n", - "318 annotators, 32K+ annotations, 12 languages - and growing!üåç\n", - "57\n", - "2 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Merve Noyan\n", - "open-sourceress at ü§ó | Google Developer Expert in Machine Learning, MSc Candidate in Data Science\n", - "22h\n", - "Report this post\n", - "Fine-tune ColPali for your multimodal RAG use case üî•\n", - "\n", - "ColPali just landed to\n", - "Hugging Face\n", - "transformers and I have built a simple fine-tuning tutorial with QLoRA ü§ó\n", - "You can fine-tune the model with 32 GB VRAM with batch size of 4 (which can run on Colab A100)\n", - "Link in comments üí¨\n", - "267\n", - "4 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "ü§ñ Avthar Sewrathan\n", - "AI and Developer Product Leader | I talk about using AI and building AI apps\n", - "1d\n", - "Report this post\n", - "TIL: You can now load any\n", - "Hugging Face\n", - "dataset into PostgreSQL with just 1 line of SQL ü§Ø\n", - "\n", - "All thanks to the pgai PostgreSQL extension. \n", - "\n", - "Shoutout to\n", - "Matvey Arye\n", - "from the\n", - "Timescale\n", - "AI engineering team for implementing this.\n", - "\n", - "Learn more about using PostgreSQL with HuggingFace datasets in the HuggingFace docs:\n", - "https://lnkd.in/eS4hqSDq\n", - "#postgresql\n", - "#huggingface\n", - "#opensource\n", - "180\n", - "14 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Argilla\n", - "10,266 followers\n", - "1d\n", - "Report this post\n", - "üé¢ Push to Hub: Export your dataset to the Hugging Face Hub directly from the Argilla UI.\n", - "\n", - "We‚Äôre super excited to announce that we've closed the loop: now you can load a dataset from the Hub, open it on\n", - "Argilla\n", - "UI, label it, and push the annotated dataset to the Hub. All this without a line of code!\n", - "\n", - "\n", - "ùó™ùóµùòÜ ùòÄùóµùóºùòÇùóπùó± ùòÜùóºùòÇ ùòÇùòÄùó≤ ùó∂ùòÅ?\n", - "\n", - "Your AI project's impact depends heavily on the effort and care you put into your data. This new feature enables you to iterate faster and make annotated data available in the right format for training and evaluation.\n", - "\n", - "\n", - "ùóõùóºùòÑ ùó±ùóºùó≤ùòÄ ùó∂ùòÅ ùòÑùóºùóøùó∏?\n", - "\n", - "1Ô∏è‚É£ Import initial data from a CSV or any format to Hugging Face\n", - "2Ô∏è‚É£ Load it into the Argilla UI and configure the annotation task\n", - "3Ô∏è‚É£ Annotate your dataset\n", - "üöÄ Click on ‚ÄúPush to Hub‚Äù and share the dataset with your team (or the entire world)\n", - "\n", - "üëâ ùó•ùó≤ùóÆùó±ùòÜ ùòÅùóº ùòÅùóøùòÜ ùó∂ùòÅ ùóºùòÇùòÅ?\n", - "\n", - "Get started here:\n", - "https://lnkd.in/dhA-swR5\n", - "Release highlights:\n", - "https://lnkd.in/dbdQXG-W\n", - "35\n", - "3 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Daniel V.\n", - "Machine Learning Librarian@ü§ó | Championing Open Science & Machine Learning\n", - "1d\n", - "Report this post\n", - "Hot take: shipping BERT-sized models in 2025 will benefit far more people than sharing an LLM overfitted to some saturated leaderboards \n", - "\n", - "We're already seeing ModernBERT finetunes on the\n", - "Hugging Face\n", - "Hub. My guess is we'll see hundreds of these by the end of 2025.\n", - "80\n", - "4 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Gradio\n", - "47,326 followers\n", - "1d\n", - "Edited\n", - "Report this post\n", - "ü§Øüî•LEARN HOW TO CREATE interactive agentic chatbots using Gradio that are capable of showcasing the Thoughts, Tasks, and interim responses of Multiple Agents as you await the final answer from your AI assistant.\n", - "\n", - "üéØ Customer Support multi-agents with\n", - "CrewAI\n", - "and\n", - "Gradio\n", - "Showcasing here, a user-friendly, high-performing multi-agent gradio app. TO operate it, simply enter a webpage URL along with your questions related to that page, and in turn receive a high-quality response from the CrewAI Multi-Agent setup.\n", - "\n", - "üöÄAccess this app on\n", - "Hugging Face\n", - "Spaces:\n", - "https://lnkd.in/g6kXp_D2\n", - "‚Ķmore\n", - "72\n", - "1 Comment\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Clem Delangue ü§ó\n", - "Clem Delangue ü§ó is an Influencer\n", - "Co-founder & CEO at Hugging Face\n", - "2d\n", - "Report this post\n", - "In the past few months, we've invested a lot of efforts in improving the user management features of the Hugging Face hub that more than 5M AI builder are now using. It helps not only for easier organization collaboration but also for security (for example to make sure ex team members don't still have access to private models). \n", - "\n", - "If your manager, VP AI or admin/CISO is not aware, mention them below so that we can connect if they have any questions or feedback as most of these features are part of the Enterprise hub subscriptions:\n", - "https://lnkd.in/e-RY-3vs\n", - ")\n", - "\n", - "Cheers!\n", - "47\n", - "3 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Clem Delangue ü§ó\n", - "Clem Delangue ü§ó is an Influencer\n", - "Co-founder & CEO at Hugging Face\n", - "4d\n", - "Report this post\n", - "Just 10 days after o1's public debut, we‚Äôre thrilled to unveil the open-source version of the groundbreaking technique behind its success: scaling test-time compute ü߆üí° \n", - "\n", - "By giving models more \"time to think,\" Llama 1B outperforms Llama 8B in math‚Äîbeating a model 8x its size. The full recipe is open-sourceü§Ø \n", - "\n", - "This is the power of open science and open-source AI! üåç‚ú®\n", - "5,292\n", - "125 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Hugging Face\n", - "reposted this\n", - "Philipp Schmid\n", - "Technical Lead & LLMs at Hugging Face ü§ó | AWS ML HERO ü¶∏ü誂ôÇÔ∏è\n", - "1d\n", - "Report this post\n", - "ModernBERT, BERT revisited in the age of LLMs and Generative AI!\n", - "LightOn\n", - "and\n", - "Answer.ai\n", - "modernized BERT! Improved architecture with 8192 context length, flash attention, and trained on 2T tokens. ModernBERT outperforms version BERT and RoBERTa versions! üëÄ\n", - "\n", - "TL;DR;\n", - "2Ô∏è‚É£¬†Comes in 2 sizes base (139M) and large (395M)\n", - "üöĬ†Better performance across all metrics than the original BERT\n", - "üìè 8,192 token context length (16x longer than BERT)\n", - "‚ö° Modern architecture with Flash Attention 2, RoPE embeddings, and alternating attention\n", - "üìö Trained on 2 trillion tokens, primarily English and Code\n", - "üí® 2-4x faster than other models with mixed-length inputs\n", - "üî쬆Released under Apache 2.0\n", - "ü§ó¬†Available on\n", - "Hugging Face\n", - "and Transformers (main)\n", - "\n", - "Models:\n", - "https://lnkd.in/ethiJ2xh\n", - "Blog:\n", - "https://lnkd.in/ebiEzb4P\n", - "Paper:\n", - "https://lnkd.in/ezR8MUBF\n", - "1,844\n", - "67 Comments\n", - "Like\n", - "Comment\n", - "Share\n", - "Join now to see what you are missing\n", - "Find people you know at Hugging Face\n", - "Browse recommended jobs for you\n", - "View all updates, news, and articles\n", - "Join now\n", - "Similar pages\n", - "Anthropic\n", - "Research Services\n", - "Mistral AI\n", - "Technology, Information and Internet\n", - "Paris, France\n", - "OpenAI\n", - "Research Services\n", - "San Francisco, CA\n", - "LangChain\n", - "Technology, Information and Internet\n", - "Perplexity\n", - "Software Development\n", - "San Francisco, California\n", - "Generative AI\n", - "Technology, Information and Internet\n", - "Google DeepMind\n", - "Research Services\n", - "London, London\n", - "LlamaIndex\n", - "Technology, Information and Internet\n", - "San Francisco, California\n", - "DeepLearning.AI\n", - "Software Development\n", - "Palo Alto, California\n", - "Cohere\n", - "Software Development\n", - "Toronto, Ontario\n", - "Show more similar pages\n", - "Show fewer similar pages\n", - "Browse jobs\n", - "Engineer jobs\n", - "555,845 open jobs\n", - "Machine Learning Engineer jobs\n", - "148,937 open jobs\n", - "Scientist jobs\n", - "48,969 open jobs\n", - "Software Engineer jobs\n", - "300,699 open jobs\n", - "Intern jobs\n", - "71,196 open jobs\n", - "Developer jobs\n", - "258,935 open jobs\n", - "Analyst jobs\n", - "694,057 open jobs\n", - "Intelligence Specialist jobs\n", - "7,156 open jobs\n", - "Manager jobs\n", - "1,880,925 open jobs\n", - "Data Scientist jobs\n", - "264,158 open jobs\n", - "Director jobs\n", - "1,220,357 open jobs\n", - "Associate jobs\n", - "1,091,945 open jobs\n", - "Python Developer jobs\n", - "46,642 open jobs\n", - "Evangelist jobs\n", - "5,068 open jobs\n", - "Data Engineer jobs\n", - "192,126 open jobs\n", - "Vice President jobs\n", - "235,270 open jobs\n", - "Quantitative Analyst jobs\n", - "19,570 open jobs\n", - "Program Manager jobs\n", - "243,900 open jobs\n", - "Data Science Specialist jobs\n", - "2,441 open jobs\n", - "Lead Software Engineer jobs\n", - "68,215 open jobs\n", - "Show more jobs like this\n", - "Show fewer jobs like this\n", - "Funding\n", - "Hugging Face\n", - "7 total rounds\n", - "Last Round\n", - "Series D\n", - "Feb 16, 2024\n", - "External Crunchbase Link for last round of funding\n", - "See more info on\n", - "crunchbase\n", - "More searches\n", - "More searches\n", - "Engineer jobs\n", - "Intern jobs\n", - "Machine Learning Engineer jobs\n", - "Software Engineer jobs\n", - "Scientist jobs\n", - "Developer jobs\n", - "Research Intern jobs\n", - "Analyst jobs\n", - "Intelligence Specialist jobs\n", - "Quantitative Analyst jobs\n", - "Technician jobs\n", - "Data Science Specialist jobs\n", - "Project Manager jobs\n", - "Summer Intern jobs\n", - "Manager jobs\n", - "Senior Staff Engineer jobs\n", - "PHD jobs\n", - "Trader jobs\n", - "Researcher jobs\n", - "Data Scientist jobs\n", - "Writer jobs\n", - "Data Analyst jobs\n", - "Product Designer jobs\n", - "Back End Developer jobs\n", - "Spring Intern jobs\n", - "Program Manager jobs\n", - "Technology Officer jobs\n", - "Software Intern jobs\n", - "Security Professional jobs\n", - "Senior Software Engineer jobs\n", - "Python Developer jobs\n", - "Engineering Manager jobs\n", - "Web Developer jobs\n", - "Graduate jobs\n", - "Full Stack Engineer jobs\n", - "Professor jobs\n", - "Head jobs\n", - "Verification Manager jobs\n", - "User Experience Designer jobs\n", - "Recruiter jobs\n", - "Chief Executive Officer jobs\n", - "Associate jobs\n", - "Support Developer jobs\n", - "Senior Firmware Engineer jobs\n", - "Marketing Manager jobs\n", - "Modeling Engineer jobs\n", - "Designer jobs\n", - "Automation Lead jobs\n", - "Options Trader jobs\n", - "Agile Coach jobs\n", - "Research Engineer jobs\n", - "Software Quality Assurance Analyst jobs\n", - "User Experience Manager jobs\n", - "Technical Intern jobs\n", - "Junior Network Engineer jobs\n", - "Information Technology Recruiter jobs\n", - "User Researcher jobs\n", - "Player jobs\n", - "Engineering Project Manager jobs\n", - "Digital Strategist jobs\n", - "LinkedIn\n", - "© 2024\n", - "About\n", - "Accessibility\n", - "User Agreement\n", - "Privacy Policy\n", - "Cookie Policy\n", - "Copyright Policy\n", - "Brand Policy\n", - "Guest Controls\n", - "Community Guidelines\n", - "ÿߟÑÿπÿ±ÿ®Ÿäÿ© (Arabic)\n", - "‡¶¨‡¶æ‡¶Ç‡¶≤‡¶æ (Bangla)\n", - "ƒåe≈°tina (Czech)\n", - "Dansk (Danish)\n", - "Deutsch (German)\n", - "ŒïŒªŒªŒ∑ŒΩŒπŒ∫Œ¨ (Greek)\n", - "English (English)\n", - "Espa√±ol (Spanish)\n", - "ŸÅÿßÿ±ÿ≥€å (Persian)\n", - "Suomi (Finnish)\n", - "Fran√ßais (French)\n", - "‡§π‡§ø‡§Ç‡§¶‡•Ä (Hindi)\n", - "Magyar (Hungarian)\n", - "Bahasa Indonesia (Indonesian)\n", - "Italiano (Italian)\n", - "◊¢◊ë◊®◊ô◊™ (Hebrew)\n", - "Êó•Êú¨Ë™û (Japanese)\n", - "Ìïú͵≠Ïñ¥ (Korean)\n", - "‡§Æ‡§∞‡§æ‡§†‡•Ä (Marathi)\n", - "Bahasa Malaysia (Malay)\n", - "Nederlands (Dutch)\n", - "Norsk (Norwegian)\n", - "‡®™‡©∞‡®ú‡®æ‡®¨‡©Ä (Punjabi)\n", - "Polski (Polish)\n", - "Portugu√™s (Portuguese)\n", - "Rom√¢nƒÉ (Romanian)\n", - "–†—É—Å—Å–∫–∏–π (Russian)\n", - "Svenska (Swedish)\n", - "‡∞§‡±Ü‡∞≤‡±Å‡∞ó‡±Å (Telugu)\n", - "‡∏†‡∏≤‡∏©‡∏≤‡πч∏ó‡∏¢ (Thai)\n", - "Tagalog (Tagalog)\n", - "T√ºrk√ße (Turkish)\n", - "–£–∫—Ä–∞—ó–Ω—Å—å–∫–∞ (Ukrainian)\n", - "Ti·∫øng Vi·ªát (Vietnamese)\n", - "ÁÆÄ‰Ωì‰∏≠Êñá (Chinese (Simplified))\n", - "Ê≠£È´î‰∏≠Êñá (Chinese (Traditional))\n", - "Language\n", - "Agree & Join LinkedIn\n", - "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", - "User Agreement\n", - ",\n", - "Privacy Policy\n", - ", and\n", - "Cookie Policy\n", - ".\n", - "Sign in to see who you already know at Hugging Face\n", - "Sign in\n", - "Welcome back\n", - "Email or phone\n", - "Password\n", - "Show\n", - "Forgot password?\n", - "Sign in\n", - "or\n", - "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", - "User Agreement\n", - ",\n", - "Privacy Policy\n", - ", and\n", - "Cookie Policy\n", - ".\n", - "New to LinkedIn?\n", - "Join now\n", - "or\n", - "New to LinkedIn?\n", - "Join now\n", - "By clicking Continue to join or sign in, you agree to LinkedIn‚Äôs\n", - "User Agreement\n", - ",\n", - "Privacy Policy\n", - ", and\n", - "Cookie Policy\n", - ".\n", - "LinkedIn\n", - "LinkedIn is better on the app\n", - "Don‚Äôt have the app? Get it in the Microsoft Store.\n", - "Open the app\n", - "\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "print(get_all_details(\"https://huggingface.co\"))" ] @@ -2674,359 +300,10 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": null, "id": "cd909e0b-1312-4ce2-a553-821e795d7572", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog', 'url': 'https://huggingface.co/blog'}, {'type': 'company page', 'url': 'https://huggingface.co/enterprise'}]}\n", - "You are looking at a company called: HuggingFace\n", - "Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\n", - "Landing page:\n", - "Webpage Title:\n", - "Hugging Face – The AI community building the future.\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "The AI community building the future.\n", - "The platform where the machine learning community collaborates on models, datasets, and applications.\n", - "Trending on\n", - "this week\n", - "Models\n", - "IamCreateAI/Ruyi-Mini-7B\n", - "Updated\n", - "4 days ago\n", - "•\n", - "8.17k\n", - "•\n", - "352\n", - "Datou1111/shou_xin\n", - "Updated\n", - "12 days ago\n", - "•\n", - "28.3k\n", - "•\n", - "672\n", - "answerdotai/ModernBERT-base\n", - "Updated\n", - "1 day ago\n", - "•\n", - "6.24k\n", - "•\n", - "236\n", - "meta-llama/Llama-3.3-70B-Instruct\n", - "Updated\n", - "11 days ago\n", - "•\n", - "236k\n", - "•\n", - "1.21k\n", - "tencent/HunyuanVideo\n", - "Updated\n", - "3 days ago\n", - "•\n", - "6.01k\n", - "•\n", - "1.2k\n", - "Browse 400k+ models\n", - "Spaces\n", - "Running\n", - "on\n", - "Zero\n", - "1.79k\n", - "🏢\n", - "TRELLIS\n", - "Scalable and Versatile 3D Generation from images\n", - "Running\n", - "306\n", - "📝\n", - "Scaling test-time compute\n", - "Running\n", - "on\n", - "Zero\n", - "470\n", - "🚀\n", - "Flux Style Shaping\n", - "Optical illusions and style transfer with FLUX\n", - "Running\n", - "on\n", - "CPU Upgrade\n", - "6.11k\n", - "👕\n", - "Kolors Virtual Try-On\n", - "Running\n", - "on\n", - "Zero\n", - "965\n", - "📈\n", - "IC Light V2\n", - "Browse 150k+ applications\n", - "Datasets\n", - "fka/awesome-chatgpt-prompts\n", - "Updated\n", - "Sep 3\n", - "•\n", - "6.83k\n", - "•\n", - "6.58k\n", - "O1-OPEN/OpenO1-SFT\n", - "Updated\n", - "4 days ago\n", - "•\n", - "1.86k\n", - "•\n", - "234\n", - "HuggingFaceFW/fineweb-2\n", - "Updated\n", - "13 days ago\n", - "•\n", - "77.7k\n", - "•\n", - "342\n", - "HuggingFaceTB/finemath\n", - "Updated\n", - "1 day ago\n", - "•\n", - "1.86k\n", - "•\n", - "43\n", - "amphora/QwQ-LongCoT-130K\n", - "Updated\n", - "16 days ago\n", - "•\n", - "1.34k\n", - "•\n", - "85\n", - "Browse 100k+ datasets\n", - "The Home of Machine Learning\n", - "Create, discover and collaborate on ML better.\n", - "The collaboration platform\n", - "Host and collaborate on unlimited public models, datasets and applications.\n", - "Move faster\n", - "With the HF Open source stack.\n", - "Explore all modalities\n", - "Text, image, video, audio or even 3D.\n", - "Build your portfolio\n", - "Share your work with the world and build your ML profile.\n", - "Sign Up\n", - "Accelerate your ML\n", - "We provide paid Compute and Enterprise solutions.\n", - "Compute\n", - "Deploy on optimized\n", - "Inference Endpoints\n", - "or update your\n", - "Spaces applications\n", - "to a GPU in a few clicks.\n", - "View pricing\n", - "Starting at $0.60/hour for GPU\n", - "Enterprise\n", - "Give your team the most advanced platform to build AI with enterprise-grade security, access controls and\n", - "\t\t\tdedicated support.\n", - "Getting started\n", - "Starting at $20/user/month\n", - "Single Sign-On\n", - "Regions\n", - "Priority Support\n", - "Audit Logs\n", - "Resource Groups\n", - "Private Datasets Viewer\n", - "More than 50,000 organizations are using Hugging Face\n", - "Ai2\n", - "Enterprise\n", - "non-profit\n", - "•\n", - "366 models\n", - "•\n", - "1.76k followers\n", - "AI at Meta\n", - "Enterprise\n", - "company\n", - "•\n", - "2.05k models\n", - "•\n", - "3.83k followers\n", - "Amazon Web Services\n", - "company\n", - "•\n", - "21 models\n", - "•\n", - "2.45k followers\n", - "Google\n", - "company\n", - "•\n", - "911 models\n", - "•\n", - "5.76k followers\n", - "Intel\n", - "company\n", - "•\n", - "217 models\n", - "•\n", - "2.07k followers\n", - "Microsoft\n", - "company\n", - "•\n", - "351 models\n", - "•\n", - "6.29k followers\n", - "Grammarly\n", - "company\n", - "•\n", - "10 models\n", - "•\n", - "102 followers\n", - "Writer\n", - "Enterprise\n", - "company\n", - "•\n", - "17 models\n", - "•\n", - "186 followers\n", - "Our Open Source\n", - "We are building the foundation of ML tooling with the community.\n", - "Transformers\n", - "136,571\n", - "State-of-the-art ML for Pytorch, TensorFlow, and JAX.\n", - "Diffusers\n", - "26,740\n", - "State-of-the-art diffusion models for image and audio generation in PyTorch.\n", - "Safetensors\n", - "2,960\n", - "Simple, safe way to store and distribute neural networks weights safely and quickly.\n", - "Hub Python Library\n", - "2,177\n", - "Client library for the HF Hub: manage repositories from your Python runtime.\n", - "Tokenizers\n", - "9,165\n", - "Fast tokenizers, optimized for both research and production.\n", - "PEFT\n", - "16,767\n", - "Parameter efficient finetuning methods for large models.\n", - "Transformers.js\n", - "12,421\n", - "State-of-the-art Machine Learning for the web. Run Transformers directly in your browser, with no need for a server.\n", - "timm\n", - "32,668\n", - "State-of-the-art computer vision models, layers, optimizers, training/evaluation, and utilities.\n", - "TRL\n", - "10,382\n", - "Train transformer language models with reinforcement learning.\n", - "Datasets\n", - "19,378\n", - "Access and share datasets for computer vision, audio, and NLP tasks.\n", - "Text Generation Inference\n", - "9,484\n", - "Toolkit to serve Large Language Models.\n", - "Accelerate\n", - "8,082\n", - "Easily train and use PyTorch models with multi-GPU, TPU, mixed-precision.\n", - "System theme\n", - "Website\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Tasks\n", - "Inference Endpoints\n", - "HuggingChat\n", - "Company\n", - "About\n", - "Brand assets\n", - "Terms of service\n", - "Privacy\n", - "Jobs\n", - "Press\n", - "Resources\n", - "Learn\n", - "Documentation\n", - "Blog\n", - "Forum\n", - "Service Status\n", - "Social\n", - "GitHub\n", - "Twitter\n", - "LinkedIn\n", - "Discord\n", - "\n", - "\n", - "\n", - "about page\n", - "Webpage Title:\n", - "Hugging Face – The AI community building the future.\n", - "Webpage Contents:\n", - "Hugging Face\n", - "Models\n", - "Datasets\n", - "Spaces\n", - "Posts\n", - "Docs\n", - "Enterprise\n", - "Pricing\n", - "Log In\n", - "Sign Up\n", - "The AI community building the future.\n", - "The platform where the machine learning community collaborates on models, datasets, and applications.\n", - "Trending on\n", - "this week\n", - "Models\n", - "IamCreateAI/Ruyi-Mini-7B\n", - "Updated\n", - "4 days ago\n", - "•\n", - "8.17k\n", - "•\n", - "352\n", - "Datou1111/shou_xin\n", - "Updated\n", - "12 days ago\n", - "•\n", - "28.3k\n", - "•\n", - "672\n", - "answerdotai/ModernBERT-base\n", - "Updated\n", - "1 day ago\n", - "•\n", - "6.24k\n", - "•\n", - "236\n", - "meta-llama/Llama-3.3-70B-Instruct\n", - "Updated\n", - "11 days ago\n", - "•\n", - "236k\n", - "•\n", - "1.21k\n", - "tencent/HunyuanVideo\n", - "Updated\n", - "3 days ago\n", - "•\n", - "6.01k\n", - "•\n", - "1.2k\n", - "Browse 400k+ models\n", - "Spaces\n", - "Running\n", - "on\n", - "Zero\n", - "1.79k\n", - "🏢\n", - "TRELLIS\n", - "Scalable and Versatile 3D Generation from images\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "print(get_brochure_user_prompt(\"HuggingFace\", \"https://huggingface.co\"))" ] @@ -3052,103 +329,10 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": null, "id": "e093444a-9407-42ae-924a-145730591a39", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'home page', 'url': 'https://huggingface.com/'}, {'type': 'about page', 'url': 'https://huggingface.com/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.com/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.com/pricing'}, {'type': 'blog page', 'url': 'https://huggingface.com/blog'}, {'type': 'community page', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" - ] - }, - { - "data": { - "text/markdown": [ - "# Hugging Face Brochure\n", - "\n", - "**Hugging Face** \n", - "*The AI community building the future.*\n", - "\n", - "---\n", - "\n", - "## About Us\n", - "Hugging Face is a pioneering platform where the machine learning community comes together to collaborate on models, datasets, and applications. With over 400,000 models and 100,000 datasets available, we empower users to create, discover, and innovate in the field of machine learning.\n", - "\n", - "### Our Mission\n", - "To accelerate the development and deployment of machine learning applications, making cutting-edge technology accessible to everyone.\n", - "\n", - "---\n", - "\n", - "## Company Culture\n", - "At Hugging Face, we believe in the power of collaboration and open-source technology. We foster an inclusive environment where every team member's input is valued, allowing for diverse ideas and perspectives. Our culture emphasizes continuous learning, innovation, and a commitment to advancing AI for the greater good.\n", - "\n", - "---\n", - "\n", - "## Customers\n", - "Hugging Face serves more than 50,000 organizations, including industry leaders such as:\n", - "\n", - "- **Amazon Web Services**\n", - "- **Meta**\n", - "- **Google**\n", - "- **Microsoft**\n", - "- **Intel**\n", - " \n", - "These organizations utilize our platform for various machine learning tasks, enhancing their workflows and outputs.\n", - "\n", - "---\n", - "\n", - "## Careers at Hugging Face\n", - "We are always on the lookout for talented individuals who are passionate about AI and machine learning. Career opportunities at Hugging Face offer:\n", - "\n", - "- A collaborative work environment\n", - "- Remote work flexibility\n", - "- Continuing education and mentorship\n", - "- Opportunities to work on impactful projects\n", - "\n", - "**Join us and help shape the future of AI!**\n", - "\n", - "---\n", - "\n", - "## Our Offerings\n", - "### Models\n", - "- Access over 400,000 machine learning models, covering a variety of tasks and technologies.\n", - "\n", - "### Datasets\n", - "- Discover and share 100,000+ datasets tailored for computer vision, audio, and NLP tasks.\n", - "\n", - "### Spaces\n", - "- Utilize our application space to run various applications including real-time projects and demonstrations.\n", - "\n", - "### Enterprise Solutions\n", - "- With dedicated support and industry-grade security, our Enterprise solutions are designed for organizations looking to implement AI at scale.\n", - "\n", - "---\n", - "\n", - "## Get Started Today!\n", - "**Sign up now** to become part of the Hugging Face community and access an array of tools to accelerate your machine learning journey. \n", - "[Sign Up Here](#)\n", - "\n", - "---\n", - "\n", - "**Stay Connected** \n", - "Follow us on our social media platforms:\n", - "- [GitHub](#)\n", - "- [Twitter](#)\n", - "- [LinkedIn](#)\n", - "- [Discord](#)\n", - "\n", - "**Hugging Face – Building the Future of AI**" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "create_brochure(\"HuggingFace\", \"https://huggingface.com\")" ] @@ -3191,178 +375,20 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": null, "id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'community discussion', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" - ] - }, - { - "data": { - "text/markdown": [ - "# Welcome to Hugging Face\n", - "\n", - "## The AI Community Building the Future\n", - "\n", - "At Hugging Face, we bring together the machine learning community to collaborate on groundbreaking models, datasets, and applications. Our platform is a vibrant hub where innovation meets practicality, empowering developers and researchers to create state-of-the-art AI solutions.\n", - "\n", - "---\n", - "\n", - "### 🏆 What We Offer\n", - "\n", - "- **Models**: Access and discover over **400k+ models** including the latest advancements in AI.\n", - "- **Datasets**: A rich collection of **100k+ datasets** tailored for various machine learning tasks.\n", - "- **Spaces**: Collaborate on applications and projects seamlessly within our community’s creative workspace.\n", - "\n", - "---\n", - "\n", - "### 🌏 Our Customers\n", - "\n", - "Join the ranks of **50,000+ organizations** leveraging Hugging Face’s offerings, including industry giants like:\n", - "- **Meta**\n", - "- **Amazon Web Services**\n", - "- **Google**\n", - "- **Microsoft**\n", - "- **Grammarly**\n", - "\n", - "These companies trust us to accelerate their machine learning initiatives and foster innovation.\n", - "\n", - "---\n", - "\n", - "### 🌱 Company Culture\n", - "\n", - "At Hugging Face, we embrace an open-source ethos, encouraging collaboration and contribution from the community. Our culture is centered around creativity, innovation, and inclusivity. We believe in empowering individuals and teams by providing the right tools and support to shape the future of AI.\n", - "\n", - "---\n", - "\n", - "### 🚀 Careers at Hugging Face\n", - "\n", - "We are on the lookout for passionate individuals to join our team! If you share our vision of an accessible AI landscape, explore the career opportunities we offer. We provide an environment that supports academic growth, teamwork, and professional development while making a meaningful impact in the machine learning realm.\n", - "\n", - "#### Current Openings Include:\n", - "- Machine Learning Engineers\n", - "- Data Scientists\n", - "- Software Developers\n", - "- Community Managers\n", - "\n", - "---\n", - "\n", - "### 💡 Join Us\n", - "\n", - "Are you ready to be part of a revolution in AI? **[Sign Up](#)** today to explore the possibilities with Hugging Face or **[Log In](#)** if you’re already part of our community.\n", - "\n", - "Let’s build the future of AI together!\n", - "\n", - "---\n", - "\n", - "*For inquiries about our enterprise solutions, pricing, or community involvement, feel free to reach out through our website.* \n", - "\n", - "**Connect with us:** \n", - "[Twitter](#) | [LinkedIn](#) | [GitHub](#) | [Forum](#)" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" ] }, { "cell_type": "code", - "execution_count": 21, + "execution_count": null, "id": "87bd1188", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'homepage', 'url': 'https://huggingface.co/'}, {'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'discussion forum', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" - ] - }, - { - "data": { - "text/markdown": [ - "\n", - "# Hugging Face: The AI Community Building the Future\n", - "\n", - "Welcome to Hugging Face, the leading collaborative platform for the machine learning community. With a robust environment designed for creating, discovering, and deploying machine learning models, datasets, and applications, Hugging Face is at the frontier of artificial intelligence innovation. \n", - "\n", - "---\n", - "\n", - "## About Us\n", - "At Hugging Face, we believe in the power of collaboration. Our platform enables users to work together on projects that range from machine-learning models to expansive datasets. With over 400,000 models and 100,000 datasets available, we provide the tools necessary to help researchers, developers, and organizations accelerate their machine learning projects.\n", - "\n", - "- **Trending Models This Week:**\n", - " - **IamCreateAI/Ruyi-Mini-7B** | 8.17k | Updated 4 days ago\n", - " - **Datou1111/shou_xin** | 28.3k | Updated 12 days ago\n", - " - **meta-llama/Llama-3.3-70B-Instruct** | 236k | Updated 11 days ago\n", - "\n", - "Explore our community-driven approach that integrates state-of-the-art tools like Transformers, DiffUsers, and PEFT (Parameter Efficient Finetuning).\n", - "\n", - "---\n", - "\n", - "## Company Culture\n", - "Hugging Face fosters a vibrant and inclusive company culture, aiming to empower individuals and teams through transparent practices and open-source methodologies. We believe in “AI for everyone,” promoting accessibility and co-creation within the AI community. \n", - "\n", - "### Why Work With Us?\n", - "- **Collaborative Environment**: Join a diverse team of experts and enthusiasts dedicated to pushing the boundaries of AI and machine learning.\n", - "- **Open Source Commitment**: Contribute to freely accessible tools that serve the global community.\n", - "- **Flexible Work**: We support remote work and provide a range of job opportunities tailored to different areas of expertise.\n", - "\n", - "---\n", - "\n", - "## Customers & Organizations\n", - "Over 50,000 organizations utilize Hugging Face in various industries, including notable names such as:\n", - "- **Meta AI**\n", - "- **Amazon Web Services**\n", - "- **Google**\n", - "- **Microsoft**\n", - "\n", - "Our enterprise solutions offer seamless integration with advanced security features, making us a trusted partner for both startups and established corporations.\n", - "\n", - "---\n", - "\n", - "## Careers at Hugging Face\n", - "We are always on the lookout for passionate individuals to join our team. Explore our open positions in areas such as software development, research, marketing, and customer support.\n", - "\n", - "- **Open Positions**: \n", - " - Machine Learning Engineer\n", - " - Data Scientist\n", - " - Community Manager\n", - "\n", - "Join us in shaping the future of AI. \n", - "\n", - "**[Explore Careers](#)**\n", - "\n", - "---\n", - "\n", - "## Join the Hugging Face Community\n", - "Whether you're looking to develop cutting-edge AI models, contribute to open-source projects, or advance your career in this dynamic field, Hugging Face is your gateway to innovation.\n", - "\n", - "**[Learn More](#)** | **[Sign Up Today](#)**\n", - "\n", - "Together, let's build the future of AI!\n", - "\n" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" ] @@ -3453,92 +479,10 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": null, "id": "744bfc05", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found links: {'links': [{'type': 'about page', 'url': 'https://openai.com/about'}, {'type': 'careers page', 'url': 'https://openai.com/careers'}]}\n" - ] - }, - { - "data": { - "text/markdown": [ - "It seems that the landing and related pages for OpenAI did not yield any specific content. However, I can create a creative and engaging brochure based on general knowledge about OpenAI. Here's a humorous and entertaining brochure written in Urdu:\n", - "\n", - "\n", - "# 🎉 اوپن اے آئی: ہوشیار robots کا دوست! 🎉\n", - "\n", - "---\n", - "\n", - "## About Us - ہمارے بارے میں:\n", - "\n", - "ہماری کمپنی اوپن اے آئی، 2015 میں بنی۔ ہم نے سوچا کہ \"کیوں نہ ایک ایسا انٹیلیجنٹ سسٹم بنائیں جو انسانوں کی مدد کرے؟\" تو ہم نے کام شروع کیا اور دیکھیں! ہم نے ایک نئی دنیا کی بنیاد رکھی۔ ہماری مشن ہے \"تمام لوگوں کے لئے AI کی طاقت کو قابل رسائی بنانا\"۔ آفاقی طاقت کو ڈھونڈتے ہیں، جیسے آپ کے فرج میں چھپے ہوئے برگر!\n", - "\n", - "---\n", - "\n", - "## What We Offer - ہم کیا پیش کرتے ہیں:\n", - "\n", - "ہم AI کے شوقین ہیں! 🤖 ہم مختلف پروڈکٹس اور سروسز پیش کرتے ہیں، جیسے کہ:\n", - "\n", - "- **GPT-3**: آپ کے سوالات کے جواب دینے کے لئے تیار!\n", - "- **تخلیقی تحریر**: جنریٹنگ آئیڈیاز جب آپ کی تخلیقیت بریک ہو جائے!\n", - "- **AI ٹولز**: آپ کی زندگی کو مزید آسان بنانے کے لئے!\n", - "\n", - "ہمارے صارفین کہتے ہیں، \"اپنی زندگی میں اوپن اے آئی کی ضرورت ہے، جیسے موٹیویشن کی ضرورت ہوتی ہے!\"\n", - "\n", - "---\n", - "\n", - "## Our Culture - ہماری ثقافت:\n", - "\n", - "ہماری کمپنی میں، ہمارا بنیادی اصول ہے: \"پیار اور انوکھا خیالات!\" 🤗 ہم نے انوکھے، تعاون پر مبنی ماحول کی بنیاد رکھی، جہاں ہر کوئی اپنی بات کہہ سکتا ہے، یہاں تک کہ ونڈو کے باہر کھڑا درخت بھی! ہم کمیونٹی کی خدمت کیلئے ہمیشہ تیار رہتے ہیں، وہ بھی سوشل میڈٰیا پر۔\n", - "\n", - "---\n", - "\n", - "## Who We Serve - ہم کس کی خدمت کرتے ہیں:\n", - "\n", - "ہم ہر اُس شخص کی خدمت کرتے ہیں جو سوپر ہیرومنٹ کی تلاش میں ہے۔ ہمارے وزیٹر، محققین، اور ٹیکنالوجی کے شوقین ہیں، اور ہمارے بہترین کلائنٹس include شامل ہیں \"بڑا دماغی جیسا سوچنے والے!\" 💡\n", - "\n", - "---\n", - "\n", - "## Join Us - ہمارے ساتھ شامل ہوں:\n", - "\n", - "آپ کو ترقی کی تلاش ہے؟ تو ہماری ٹیم کا حصہ بنیں! 🚀 ہم ہمیشہ نئے امریکی جاموں کی تلاش میں ہیں۔ آپ کو ٹریننگ، ترقی کے مواقع، اور سہولیات فراہم کریں گے۔\n", - "\n", - "📩 **درخواست دینے کے مرحلے:** ہماری ویب سائٹ پر جائیں، کیونکہ ہم جانتے ہیں کہ آپ کا خواب آپ کے قریب ہے!\n", - "\n", - "---\n", - "\n", - "## Contact Us - ہم سے رابطہ کریں:\n", - "\n", - "**پتہ:** نیٹ ورک کی دنیا \n", - "**فون:** 123-456-789 \n", - "**ایمیل:** info@openai.com \n", - "**سوشل میڈیا:** [فیس بک](#) | [ٹویٹر](#) | [لنکڈ ان](#) \n", - "**ویب سائٹ:** [openai.com](#)\n", - "\n", - "---\n", - "\n", - "## Closing Note - اختتامی نوٹ:\n", - "\n", - "ہماری کمپنی اوپن اے آئی کی طرف سے ایک شکریہ! اے آئی کی دنیا میں قدم رکھنے کا وقت آ گیا ہے! \n", - "\n", - "🖱️ **آج ہی رابطہ کریں یا ہماری ویب سائٹ کا دورہ کریں!**\n", - "\n", - "\n", - "**نوٹ:** واقعی ویب سائٹ کے مخصوص روابط، ای میل اور نمبر تخلیقی مقصد کے لئے ہیں۔ اس کو حقیقی معلومات کے ساتھ تبدیل کیا جا سکتا ہے۔" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "\n", "multi_lingual_stream_brochure(\"OpenAI\", \"https://openai.com/\", \"Urdu\", \"humorous, entertaining, jokey\")" @@ -3551,14 +495,6 @@ "metadata": {}, "outputs": [], "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "4fb86dc6", - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { From db429806bc15946513cefa605bfcb7885b4a3571 Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:22:20 +1100 Subject: [PATCH 3/6] Day 5 Challend one with multilingual aloing with multitone --- .../day5-multi-lingual-desire-format.ipynb | 8 -------- 1 file changed, 8 deletions(-) diff --git a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb index b17c402..17e1094 100644 --- a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb +++ b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb @@ -487,14 +487,6 @@ "\n", "multi_lingual_stream_brochure(\"OpenAI\", \"https://openai.com/\", \"Urdu\", \"humorous, entertaining, jokey\")" ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "b6f1e8d9", - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { From 7b38868ddee956bb89b85137e71e3df5820c4e14 Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:38:47 +1100 Subject: [PATCH 4/6] Rename accendently --- ...-format.ipynb => day5-multi-lingual-desire-format.ipynb.ipynb} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename week1/community-contributions/{day5-multi-lingual-desire-format.ipynb => day5-multi-lingual-desire-format.ipynb.ipynb} (100%) diff --git a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb b/week1/community-contributions/day5-multi-lingual-desire-format.ipynb.ipynb similarity index 100% rename from week1/community-contributions/day5-multi-lingual-desire-format.ipynb rename to week1/community-contributions/day5-multi-lingual-desire-format.ipynb.ipynb From 8b52eab336c56c64ef96eef44f841d487cb6563f Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:43:47 +1100 Subject: [PATCH 5/6] Renamed day5-multi-lingual-desire-format.ipynb to day5-MultiLingual-MultiTone.ipynb --- ...esire-format.ipynb.ipynb => day5-MultiLingual-MultiTone.ipynb} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename week1/community-contributions/{day5-multi-lingual-desire-format.ipynb.ipynb => day5-MultiLingual-MultiTone.ipynb} (100%) diff --git a/week1/community-contributions/day5-multi-lingual-desire-format.ipynb.ipynb b/week1/community-contributions/day5-MultiLingual-MultiTone.ipynb similarity index 100% rename from week1/community-contributions/day5-multi-lingual-desire-format.ipynb.ipynb rename to week1/community-contributions/day5-MultiLingual-MultiTone.ipynb From 7446459510a6154c88c08f79739b87b050aa6245 Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Sun, 22 Dec 2024 01:47:59 +1100 Subject: [PATCH 6/6] Update the code and did final changes --- week1/community-contributions/day5-MultiLingual-MultiTone.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/week1/community-contributions/day5-MultiLingual-MultiTone.ipynb b/week1/community-contributions/day5-MultiLingual-MultiTone.ipynb index 17e1094..6e07f60 100644 --- a/week1/community-contributions/day5-MultiLingual-MultiTone.ipynb +++ b/week1/community-contributions/day5-MultiLingual-MultiTone.ipynb @@ -398,7 +398,7 @@ "id": "a9e7375d", "metadata": {}, "source": [ - "## **Multi-lingual with Desire Format**\n" + "## **Multi-lingual with Multi-Tone in Desire Format**" ] }, {