{ "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(override=True)\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": 10, "id": "e30d8128-933b-44cc-81c8-ab4c9d86589a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['/',\n", " '/',\n", " '/advancing-ai/why-ai/',\n", " '/advancing-ai/milestones',\n", " '/advancing-ai/research/',\n", " '/advancing-ai/social-impact/',\n", " '/advancing-ai/why-ai/',\n", " '/advancing-ai/milestones',\n", " '/advancing-ai/research/',\n", " '/advancing-ai/social-impact/',\n", " '/responsibility/principles/',\n", " '/responsibility/safety/',\n", " '/responsibility/public-policy-perspectives/',\n", " '/responsibility/building-for-everyone/',\n", " '/responsibility/principles/',\n", " '/responsibility/safety/',\n", " '/responsibility/public-policy-perspectives/',\n", " '/responsibility/building-for-everyone/',\n", " '/get-started/gemini-ecosystem/',\n", " '/get-started/products/',\n", " 'https://labs.google/',\n", " '/get-started/for-developers/',\n", " '/get-started/our-models/',\n", " '/get-started/for-organizations/',\n", " '/get-started/gemini-ecosystem/',\n", " '/get-started/products/',\n", " 'https://labs.google/',\n", " '/get-started/for-developers/',\n", " '/get-started/our-models/',\n", " '/get-started/for-organizations/',\n", " '/applied-ai/health/',\n", " '/applied-ai/science/',\n", " '/applied-ai/sustainability/',\n", " 'https://quantumai.google/',\n", " '/applied-ai/health/',\n", " '/applied-ai/science/',\n", " '/applied-ai/sustainability/',\n", " 'https://quantumai.google/',\n", " '/latest-news/',\n", " '/get-started/gemini-ecosystem/',\n", " '#section-1',\n", " '#section-2',\n", " '#section-3',\n", " '#section-4',\n", " 'https://deepmind.google/technologies/project-astra/',\n", " 'https://gemini.google.com/',\n", " 'https://search.google/ai-on-search/',\n", " 'https://notebooklm.google/?utm_source=gono&utm_medium=web&utm_campaign=aigooglepage',\n", " 'https://workspace.google.com/solutions/ai/',\n", " 'https://aitestkitchen.withgoogle.com/tools/image-fx',\n", " 'https://blog.google/products/photos/google-ask-photos-early-access/',\n", " 'https://store.google.com/intl/en/ideas/articles/what-is-an-ai-camera/',\n", " 'https://aloud.area120.google.com/?utm_source=redirect&utm_medium=aloudai&utm_campaign=0817',\n", " 'https://grow.google/career-dreamer?utm_source=google&utm_medium=owned&utm_campaign=2025-career-dreamer__geo--Global&utm_content=ai-google-homepage-carousel',\n", " '/get-started/gemini-ecosystem',\n", " '/get-started/gemini-ecosystem',\n", " 'https://www.android.com/ai/',\n", " '/get-started/for-developers',\n", " '/get-started/for-organizations',\n", " '/responsibility/principles/',\n", " '/responsibility/principles/#our-ai-principles-in-action',\n", " '/advancing-ai/social-impact/',\n", " '/advancing-ai/social-impact/',\n", " 'https://deepmind.google/technologies/alphafold/',\n", " 'https://sites.research.google/relate/',\n", " 'https://blog.google/technology/research/google-ai-research-new-images-human-brain/',\n", " 'https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/',\n", " 'https://deepmind.google/technologies/alphafold/',\n", " 'https://sites.research.google/relate/',\n", " 'https://blog.google/technology/research/google-ai-research-new-images-human-brain/',\n", " 'https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/',\n", " '/advancing-ai/milestones/',\n", " 'https://blog.google/technology/ai/?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://blog.google/products/gemini/tips-how-to-use-deep-research/?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://blog.google/products/gemini/gemini-collaboration-features/?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://blog.google/technology/developers/gemma-3/?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://blog.google/technology/health/the-check-up-health-ai-updates-2025/?utm_source=ai.google&utm_medium=referral&utm_campaign=og',\n", " 'https://deepmind.google/',\n", " 'https://research.google/',\n", " 'https://cloud.google.com/?hl=en',\n", " 'https://labs.google/',\n", " 'https://www.google.com',\n", " 'https://www.google.com/intl/en/policies/privacy/',\n", " 'https://www.google.com/intl/en/policies/terms/',\n", " 'https://about.google/',\n", " 'https://about.google/products/']" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "site = Website(\"https://ai.google/\")\n", "site.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": 11, "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": 12, "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": 13, "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": 14, "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://ai.google/ - 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", "/\n", "/\n", "/advancing-ai/why-ai/\n", "/advancing-ai/milestones\n", "/advancing-ai/research/\n", "/advancing-ai/social-impact/\n", "/advancing-ai/why-ai/\n", "/advancing-ai/milestones\n", "/advancing-ai/research/\n", "/advancing-ai/social-impact/\n", "/responsibility/principles/\n", "/responsibility/safety/\n", "/responsibility/public-policy-perspectives/\n", "/responsibility/building-for-everyone/\n", "/responsibility/principles/\n", "/responsibility/safety/\n", "/responsibility/public-policy-perspectives/\n", "/responsibility/building-for-everyone/\n", "/get-started/gemini-ecosystem/\n", "/get-started/products/\n", "https://labs.google/\n", "/get-started/for-developers/\n", "/get-started/our-models/\n", "/get-started/for-organizations/\n", "/get-started/gemini-ecosystem/\n", "/get-started/products/\n", "https://labs.google/\n", "/get-started/for-developers/\n", "/get-started/our-models/\n", "/get-started/for-organizations/\n", "/applied-ai/health/\n", "/applied-ai/science/\n", "/applied-ai/sustainability/\n", "https://quantumai.google/\n", "/applied-ai/health/\n", "/applied-ai/science/\n", "/applied-ai/sustainability/\n", "https://quantumai.google/\n", "/latest-news/\n", "/get-started/gemini-ecosystem/\n", "#section-1\n", "#section-2\n", "#section-3\n", "#section-4\n", "https://deepmind.google/technologies/project-astra/\n", "https://gemini.google.com/\n", "https://search.google/ai-on-search/\n", "https://notebooklm.google/?utm_source=gono&utm_medium=web&utm_campaign=aigooglepage\n", "https://workspace.google.com/solutions/ai/\n", "https://aitestkitchen.withgoogle.com/tools/image-fx\n", "https://blog.google/products/photos/google-ask-photos-early-access/\n", "https://store.google.com/intl/en/ideas/articles/what-is-an-ai-camera/\n", "https://aloud.area120.google.com/?utm_source=redirect&utm_medium=aloudai&utm_campaign=0817\n", "https://grow.google/career-dreamer?utm_source=google&utm_medium=owned&utm_campaign=2025-career-dreamer__geo--Global&utm_content=ai-google-homepage-carousel\n", "/get-started/gemini-ecosystem\n", "/get-started/gemini-ecosystem\n", "https://www.android.com/ai/\n", "/get-started/for-developers\n", "/get-started/for-organizations\n", "/responsibility/principles/\n", "/responsibility/principles/#our-ai-principles-in-action\n", "/advancing-ai/social-impact/\n", "/advancing-ai/social-impact/\n", "https://deepmind.google/technologies/alphafold/\n", "https://sites.research.google/relate/\n", "https://blog.google/technology/research/google-ai-research-new-images-human-brain/\n", "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/\n", "https://deepmind.google/technologies/alphafold/\n", "https://sites.research.google/relate/\n", "https://blog.google/technology/research/google-ai-research-new-images-human-brain/\n", "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/\n", "/advancing-ai/milestones/\n", "https://blog.google/technology/ai/?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://blog.google/products/gemini/tips-how-to-use-deep-research/?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://blog.google/products/gemini/gemini-collaboration-features/?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://blog.google/technology/developers/gemma-3/?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://blog.google/technology/health/the-check-up-health-ai-updates-2025/?utm_source=ai.google&utm_medium=referral&utm_campaign=og\n", "https://deepmind.google/\n", "https://research.google/\n", "https://cloud.google.com/?hl=en\n", "https://labs.google/\n", "https://www.google.com\n", "https://www.google.com/intl/en/policies/privacy/\n", "https://www.google.com/intl/en/policies/terms/\n", "https://about.google/\n", "https://about.google/products/\n" ] } ], "source": [ "print(get_links_user_prompt(site))" ] }, { "cell_type": "code", "execution_count": 16, "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": 17, "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", " '/spaces',\n", " '/models',\n", " '/deepseek-ai/DeepSeek-V3-0324',\n", " '/Qwen/Qwen2.5-Omni-7B',\n", " '/manycore-research/SpatialLM-Llama-1B',\n", " '/ByteDance/InfiniteYou',\n", " '/ds4sd/SmolDocling-256M-preview',\n", " '/models',\n", " '/spaces/ByteDance/InfiniteYou-FLUX',\n", " '/spaces/3DAIGC/LHM',\n", " '/spaces/Trudy/gemini-codrawing',\n", " '/spaces/tencent/Hunyuan-T1',\n", " '/spaces/stabilityai/stable-virtual-camera',\n", " '/spaces',\n", " '/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset-v1',\n", " '/datasets/glaiveai/reasoning-v1-20m',\n", " '/datasets/FreedomIntelligence/medical-o1-reasoning-SFT',\n", " '/datasets/a-m-team/AM-DeepSeek-R1-Distilled-1.4M',\n", " '/datasets/facebook/collaborative_agent_bench',\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/trl',\n", " '/docs/transformers.js',\n", " '/docs/smolagents',\n", " '/docs/peft',\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": 17, "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": 18, "id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'},\n", " {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'},\n", " {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'},\n", " {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'},\n", " {'type': 'blog page', 'url': 'https://huggingface.co/blog'},\n", " {'type': 'models page', 'url': 'https://huggingface.co/models'},\n", " {'type': 'datasets page', 'url': 'https://huggingface.co/datasets'},\n", " {'type': 'spaces page', 'url': 'https://huggingface.co/spaces'},\n", " {'type': 'documentation page', 'url': 'https://huggingface.co/docs'}]}" ] }, "execution_count": 18, "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": 19, "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": 20, "id": "5099bd14-076d-4745-baf3-dac08d8e5ab2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'models page', 'url': 'https://huggingface.co/models'}, {'type': 'datasets page', 'url': 'https://huggingface.co/datasets'}, {'type': 'spaces page', 'url': 'https://huggingface.co/spaces'}]}\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", "Explore AI Apps\n", "or\n", "Browse 1M+ models\n", "Trending on\n", "this week\n", "Models\n", "deepseek-ai/DeepSeek-V3-0324\n", "Updated\n", "1 day ago\n", "•\n", "47.6k\n", "•\n", "1.91k\n", "Qwen/Qwen2.5-Omni-7B\n", "Updated\n", "about 2 hours ago\n", "•\n", "16.3k\n", "•\n", "712\n", "manycore-research/SpatialLM-Llama-1B\n", "Updated\n", "7 days ago\n", "•\n", "6.85k\n", "•\n", "760\n", "ByteDance/InfiniteYou\n", "Updated\n", "3 days ago\n", "•\n", "448\n", "ds4sd/SmolDocling-256M-preview\n", "Updated\n", "5 days ago\n", "•\n", "44.8k\n", "•\n", "1.01k\n", "Browse 1M+ models\n", "Spaces\n", "Running\n", "on\n", "Zero\n", "493\n", "493\n", "InfiniteYou-FLUX\n", "📸\n", "Flexible Photo Recrafting While Preserving Your Identity\n", "Running\n", "on\n", "Zero\n", "211\n", "211\n", "LHM\n", "⚡\n", "Large Animatable Human Model\n", "Running\n", "331\n", "331\n", "Gemini Co-Drawing\n", "✏\n", "Gemini 2.0 native image generation co-doodling\n", "Running\n", "167\n", "167\n", "Hunyuan T1\n", "💬\n", "Hunyuan T1模型体验\n", "Running\n", "on\n", "L40S\n", "328\n", "328\n", "Stable Virtual Camera\n", "⚡\n", "Generate virtual camera views from input images\n", "Browse 400k+ applications\n", "Datasets\n", "nvidia/Llama-Nemotron-Post-Training-Dataset-v1\n", "Updated\n", "10 days ago\n", "•\n", "7.64k\n", "•\n", "258\n", "glaiveai/reasoning-v1-20m\n", "Updated\n", "9 days ago\n", "•\n", "6.31k\n", "•\n", "119\n", "FreedomIntelligence/medical-o1-reasoning-SFT\n", "Updated\n", "Feb 22\n", "•\n", "26.3k\n", "•\n", "568\n", "a-m-team/AM-DeepSeek-R1-Distilled-1.4M\n", "Updated\n", "about 3 hours ago\n", "•\n", "2.98k\n", "•\n", "72\n", "facebook/collaborative_agent_bench\n", "Updated\n", "9 days ago\n", "•\n", "89\n", "•\n", "47\n", "Browse 250k+ 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", "396 models\n", "•\n", "2.97k followers\n", "AI at Meta\n", "Enterprise\n", "company\n", "•\n", "2.07k models\n", "•\n", "5.28k followers\n", "Amazon\n", "company\n", "•\n", "10 models\n", "•\n", "2.91k followers\n", "Google\n", "company\n", "•\n", "974 models\n", "•\n", "10.6k followers\n", "Intel\n", "company\n", "•\n", "219 models\n", "•\n", "2.37k followers\n", "Microsoft\n", "company\n", "•\n", "365 models\n", "•\n", "10.7k followers\n", "Grammarly\n", "Enterprise\n", "company\n", "•\n", "10 models\n", "•\n", "146 followers\n", "Writer\n", "Enterprise\n", "company\n", "•\n", "21 models\n", "•\n", "253 followers\n", "Our Open Source\n", "We are building the foundation of ML tooling with the community.\n", "Transformers\n", "142,079\n", "State-of-the-art ML for PyTorch, TensorFlow, JAX\n", "Diffusers\n", "28,301\n", "State-of-the-art Diffusion models in PyTorch\n", "Safetensors\n", "3,189\n", "Safe way to store/distribute neural network weights\n", "Hub Python Library\n", "2,471\n", "Python client to interact with the Hugging Face Hub\n", "Tokenizers\n", "9,538\n", "Fast tokenizers optimized for research & production\n", "TRL\n", "12,895\n", "Train transformers LMs with reinforcement learning\n", "Transformers.js\n", "13,312\n", "State-of-the-art ML running directly in your browser\n", "smolagents\n", "15,929\n", "Smol library to build great agents in Python\n", "PEFT\n", "17,930\n", "Parameter-efficient finetuning for large language models\n", "Datasets\n", "19,892\n", "Access & share datasets for any ML tasks\n", "Text Generation Inference\n", "9,938\n", "Serve language models with TGI optimized toolkit\n", "Accelerate\n", "8,544\n", "Train 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", "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", "28,162\n", "AI & ML interests\n", "The AI community building the future.\n", "Recent Activity\n", "coyotte508\n", "new\n", "activity\n", "34 minutes ago\n", "huggingface/HuggingDiscussions:\n", "[FEEDBACK] Notifications\n", "Wauplin\n", "updated\n", "a dataset\n", "about 1 hour ago\n", "huggingface/documentation-images\n", "lysandre\n", "updated\n", "a dataset\n", "about 2 hours ago\n", "huggingface/transformers-metadata\n", "View all activity\n", "Articles\n", "Yay! Organizations can now publish blog Articles\n", "Jan 20\n", "•\n", "37\n", "Team members\n", "211\n", "+177\n", "+164\n", "+143\n", "+133\n", "+113\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, 2024\n", "•\n", "495k\n", "•\n", "•\n", "38\n", "distilbert/distilbert-base-uncased\n", "Fill-Mask\n", "•\n", "Updated\n", "May 6, 2024\n", "•\n", "11.9M\n", "•\n", "•\n", "653\n", "distilbert/distilbert-base-multilingual-cased\n", "Fill-Mask\n", "•\n", "Updated\n", "May 6, 2024\n", "•\n", "2.33M\n", "•\n", "•\n", "182\n", "distilbert/distilbert-base-uncased-finetuned-sst-2-english\n", "Text Classification\n", "•\n", "Updated\n", "Dec 19, 2023\n", "•\n", "7.07M\n", "•\n", "•\n", "720\n", "spaces\n", "26\n", "Sort: \n", "\t\tRecently updated\n", "pinned\n", "Running\n", "77\n", "Number Tokenization Blog\n", "📈\n", "Explore how tokenization affects arithmetic in LLMs\n", "huggingface\n", "Dec 14, 2024\n", "Running\n", "Space Build\n", "🐨\n", "Generate static files for spaces\n", "huggingface\n", "about 4 hours ago\n", "Running\n", "6\n", "InferenceSupport\n", "💥\n", "Discussions about the Inference Providers feature on the Hub\n", "huggingface\n", "1 day ago\n", "Running\n", "134\n", "Inference Playground\n", "🔋\n", "Set webpage theme based on user preference or system settings\n", "huggingface\n", "2 days ago\n", "Running\n", "347\n", "AI Deadlines\n", "⚡\n", "Schedule tasks efficiently using AI-generated deadlines\n", "huggingface\n", "13 days ago\n", "Running\n", "533\n", "Open Source Ai Year In Review 2024\n", "😻\n", "What happened in open-source AI this year, and what’s next?\n", "huggingface\n", "Jan 8\n", "Expand 26\n", "\t\t\t\t\t\t\tspaces\n", "models\n", "16\n", "Sort: \n", "\t\tRecently updated\n", "huggingface/timesfm-tourism-monthly\n", "Updated\n", "Dec 9, 2024\n", "•\n", "268\n", "•\n", "1\n", "huggingface/CodeBERTa-language-id\n", "Text Classification\n", "•\n", "Updated\n", "Mar 29, 2024\n", "•\n", "7.14k\n", "•\n", "•\n", "59\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", "41.2k\n", "•\n", "9\n", "huggingface/distilbert-base-uncased-finetuned-mnli\n", "Text Classification\n", "•\n", "Updated\n", "Mar 22, 2023\n", "•\n", "231\n", "•\n", "•\n", "2\n", "huggingface/informer-tourism-monthly\n", "Updated\n", "Feb 24, 2023\n", "•\n", "40.6k\n", "•\n", "6\n", "huggingface/time-series-transformer-tourism-monthly\n", "Updated\n", "Feb 23, 2023\n", "•\n", "4.87k\n", "•\n", "20\n", "huggingface/the-no-branch-repo\n", "Text-to-Image\n", "•\n", "Updated\n", "Feb 10, 2023\n", "•\n", "23\n", "•\n", "4\n", "huggingface/CodeBERTa-small-v1\n", "Fill-Mask\n", "•\n", "Updated\n", "Jun 27, 2022\n", "•\n", "36.3k\n", "•\n", "80\n", "huggingface/test-model-repo\n", "Updated\n", "Nov 19, 2021\n", "•\n", "1\n", "Expand 16\n", "\t\t\t\t\t\t\tmodels\n", "datasets\n", "42\n", "Sort: \n", "\t\tRecently updated\n", "huggingface/documentation-images\n", "Viewer\n", "•\n", "Updated\n", "about 1 hour ago\n", "•\n", "52\n", "•\n", "4.33M\n", "•\n", "55\n", "huggingface/transformers-metadata\n", "Viewer\n", "•\n", "Updated\n", "about 2 hours ago\n", "•\n", "1.59k\n", "•\n", "1.86k\n", "•\n", "19\n", "huggingface/policy-docs\n", "Updated\n", "8 days ago\n", "•\n", "2.64k\n", "•\n", "10\n", "huggingface/diffusers-metadata\n", "Viewer\n", "•\n", "Updated\n", "13 days ago\n", "•\n", "69\n", "•\n", "612\n", "•\n", "6\n", "huggingface/gemini-results-2025-03-03\n", "Viewer\n", "•\n", "Updated\n", "25 days ago\n", "•\n", "17\n", "•\n", "60\n", "huggingface/gemini-results-2025-02-28\n", "Viewer\n", "•\n", "Updated\n", "28 days ago\n", "•\n", "21\n", "•\n", "53\n", "huggingface/gemini-results-2025-02-27\n", "Viewer\n", "•\n", "Updated\n", "28 days ago\n", "•\n", "24\n", "•\n", "57\n", "huggingface/gemini-results-2025-02-25\n", "Viewer\n", "•\n", "Updated\n", "about 1 month ago\n", "•\n", "32\n", "•\n", "62\n", "huggingface/gemini-results-2025-02-24\n", "Viewer\n", "•\n", "Updated\n", "Feb 25\n", "•\n", "32\n", "•\n", "63\n", "huggingface/gemini-results-2025-02-21\n", "Viewer\n", "•\n", "Updated\n", "Feb 22\n", "•\n", "29\n", "•\n", "154\n", "•\n", "1\n", "Expand 42\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", "careers page\n", "Webpage Title:\n", "Hugging Face - Current Openings\n", "Webpage Contents:\n", "\n", "\n", "\n", "\n", "enterprise page\n", "Webpage Title:\n", "Enterprise Hub - 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", "Enterprise Hub\n", "Enterprise-ready version of the world’s leading AI platform\n", "Subscribe to\n", "Enterprise Hub\n", "for $20/user/month with your Hub organization\n", "Give your organization the most advanced platform to build AI with enterprise-grade security, access controls,\n", "\t\t\tdedicated support and more.\n", "Single Sign-On\n", "Connect securely to your identity provider with SSO integration.\n", "Regions\n", "Select, manage, and audit the location of your repository data.\n", "Audit Logs\n", "Stay in control with comprehensive logs that report on actions taken.\n", "Resource Groups\n", "Accurately manage access to repositories with granular access control.\n", "Token Management\n", "Centralized token control and custom approval policies for organization access.\n", "Analytics\n", "Track and analyze repository usage data in a single dashboard.\n", "Advanced Compute Options\n", "Increase scalability and performance with more compute options like ZeroGPU.\n", "ZeroGPU Quota Boost\n", "All organization members get 5x more ZeroGPU quota to get the most of Spaces.\n", "Private Datasets Viewer\n", "Enable the Dataset Viewer on your private datasets for easier collaboration.\n", "Advanced security\n", "Configure organization-wide security policies and default repository visibility.\n", "Billing\n", "Control your budget effectively with managed billing and yearly commit options.\n", "Priority Support\n", "Maximize your platform usage with priority support from the Hugging Face team.\n", "Extra Private Storage\n", "Get an additional 1 TB of private storage for each member of your organization (then $25/month per extra TB).\n", "Join the most forward-thinking AI organizations\n", "Everything you already know and love about Hugging Face in Enterprise mode.\n", "Subscribe to\n", "Enterprise Hub\n", "or\n", "Talk to sales\n", "NVIDIA\n", "Enterprise\n", "company\n", "•\n", "329 models\n", "•\n", "20.3k followers\n", "Nerdy Face\n", "Enterprise\n", "company\n", "•\n", "1 model\n", "•\n", "286 followers\n", "AMD\n", "Enterprise\n", "company\n", "•\n", "100 models\n", "•\n", "1.43k followers\n", "Arm\n", "Enterprise\n", "company\n", "•\n", "159 followers\n", "ServiceNow-AI\n", "Enterprise\n", "company\n", "•\n", "194 followers\n", "Fidelity Investments\n", "Enterprise\n", "company\n", "•\n", "132 followers\n", "Mistral AI_\n", "Enterprise\n", "company\n", "•\n", "26 models\n", "•\n", "7.14k followers\n", "Technology Innovation Institute\n", "Enterprise\n", "company\n", "•\n", "65 models\n", "•\n", "1.27k followers\n", "Chegg Inc\n", "Enterprise\n", "company\n", "•\n", "84 followers\n", "Grammarly\n", "Enterprise\n", "company\n", "•\n", "10 models\n", "•\n", "146 followers\n", "Arcee AI\n", "Enterprise\n", "company\n", "•\n", "156 models\n", "•\n", "477 followers\n", "Widn AI\n", "Enterprise\n", "company\n", "•\n", "43 followers\n", "Adyen\n", "Enterprise\n", "company\n", "•\n", "57 followers\n", "Ekimetrics\n", "Enterprise\n", "company\n", "•\n", "55 followers\n", "Meta Llama\n", "Enterprise\n", "company\n", "•\n", "57 models\n", "•\n", "34.1k followers\n", "Snowflake\n", "Enterprise\n", "company\n", "•\n", "15 models\n", "•\n", "466 followers\n", "Orange\n", "Enterprise\n", "company\n", "•\n", "7 models\n", "•\n", "198 followers\n", "Writer\n", "Enterprise\n", "company\n", "•\n", "21 models\n", "•\n", "253 followers\n", "Deutsche Telekom AG\n", "Enterprise\n", "company\n", "•\n", "7 models\n", "•\n", "135 followers\n", "Jusbrasil\n", "Enterprise\n", "company\n", "•\n", "89 followers\n", "TNG Technology Consulting GmbH\n", "Enterprise\n", "company\n", "•\n", "1 model\n", "•\n", "65 followers\n", "IBM Granite\n", "Enterprise\n", "company\n", "•\n", "94 models\n", "•\n", "1.33k followers\n", "creditkarma\n", "Enterprise\n", "company\n", "•\n", "53 followers\n", "HiddenLayer\n", "Enterprise\n", "company\n", "•\n", "1 model\n", "•\n", "65 followers\n", "MiniMax\n", "Enterprise\n", "company\n", "•\n", "2 models\n", "•\n", "594 followers\n", "BCG X\n", "Enterprise\n", "company\n", "•\n", "37 followers\n", "Kakao Corp.\n", "Enterprise\n", "company\n", "•\n", "3 models\n", "•\n", "109 followers\n", "Twelve Labs\n", "Enterprise\n", "company\n", "•\n", "40 followers\n", "Shopify\n", "Enterprise\n", "company\n", "•\n", "429 followers\n", "AI at Meta\n", "Enterprise\n", "company\n", "•\n", "2.07k models\n", "•\n", "5.28k followers\n", "Together\n", "Enterprise\n", "company\n", "•\n", "32 models\n", "•\n", "550 followers\n", "Xsolla\n", "Enterprise\n", "company\n", "•\n", "120 followers\n", "Toyota Research Institute\n", "Enterprise\n", "company\n", "•\n", "10 models\n", "•\n", "104 followers\n", "Mercedes-Benz AG\n", "Enterprise\n", "company\n", "•\n", "142 followers\n", "H2O.ai\n", "Enterprise\n", "company\n", "•\n", "72 models\n", "•\n", "407 followers\n", "Aledade Inc\n", "Enterprise\n", "company\n", "•\n", "64 followers\n", "Nutanix\n", "Enterprise\n", "company\n", "•\n", "262 models\n", "•\n", "65 followers\n", "Johnson & Johnson\n", "Enterprise\n", "company\n", "•\n", "56 followers\n", "Stability AI\n", "Enterprise\n", "company\n", "•\n", "104 models\n", "•\n", "19.6k followers\n", "Liquid AI\n", "Enterprise\n", "company\n", "•\n", "116 followers\n", "Gretel.ai\n", "Enterprise\n", "company\n", "•\n", "9 models\n", "•\n", "112 followers\n", "NewMindAI\n", "Enterprise\n", "company\n", "•\n", "36 followers\n", "Compliance & Certifications\n", "GDPR Compliant\n", "SOC 2 Type 2\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", "pricing page\n", "Webpage Title:\n", "Hugging Face – Pricing\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", "Pricing\n", "Leveling up AI collaboration and compute.\n", "Users and organizations already use the Hub as a collaboration platform,\n", "we’re making it easy to seamlessly and scalably launch ML compute directly from the Hub.\n", "HF Hub\n", "Collaborate on Machine Learning\n", "Host unlimited public models, datasets\n", "Create unlimited orgs with no member limits\n", "Access the latest ML tools and open source\n", "Community support\n", "Forever\n", "Free\n", "PRO\n", "Pro Account\n", "Unlock advanced HF features\n", "ZeroGPU and Dev Mode for Spaces\n", "Free credits across all Inference Providers\n", "Get early access to upcoming features\n", "Show your support with a Pro badge\n", "Subscribe for\n", "$9\n", "/month\n", "Enterprise Hub\n", "Accelerate your AI roadmap\n", "SSO and SAML support\n", "Select data location with Storage Regions\n", "Precise actions reviews with Audit logs\n", "Granular access control with Resource groups\n", "Centralized token control and approval\n", "Dataset Viewer for private datasets\n", "Advanced compute options for Spaces\n", "5x more ZeroGPU quota for all org members\n", "Deploy Inference on your own Infra\n", "Managed billing with yearly commits\n", "Priority support\n", "Starting at\n", "$20\n", "per user per month\n", "Spaces Hardware\n", "Upgrade your Space compute\n", "Free CPUs\n", "Build more advanced Spaces\n", "7 optimized hardware available\n", "From CPU to GPU to Accelerators\n", "Starting at\n", "$0\n", "/hour\n", "Inference Endpoints\n", "Deploy models on fully managed infrastructure\n", "Deploy dedicated Endpoints in seconds\n", "Keep your costs low\n", "Fully-managed autoscaling\n", "Enterprise security\n", "Starting at\n", "$0.032\n", "/hour\n", "Need support to accelerate AI in your organization? View our\n", "Expert Support\n", ".\n", "Hugging Face Hub\n", "free\n", "The HF Hub is the central place to explore, experiment, collaborate and build technology with Machine\n", "\t\t\t\t\tLearning.\n", "Join the open source Machine Learning movement!\n", "→\n", "Sign Up\n", "Create with ML\n", "Packed with ML features, like model eval, dataset viewer and much more.\n", "Collaborate\n", "Git based and designed for collaboration at its core.\n", "Play and learn\n", "Learn by experimenting and sharing with our awesome community.\n", "Build your ML portfolio\n", "Share your work with the world and build your own ML profile.\n", "Spaces Hardware\n", "Starting at $0\n", "Spaces are one of the most popular ways to share ML applications and demos with the world.\n", "Upgrade your Spaces with our selection of custom on-demand hardware:\n", "→\n", "Get started with Spaces\n", "Name\n", "CPU\n", "Memory\n", "Accelerator\n", "VRAM\n", "Hourly price\n", "CPU Basic\n", "2 vCPU\n", "16 GB\n", "-\n", "-\n", "FREE\n", "CPU Upgrade\n", "8 vCPU\n", "32 GB\n", "-\n", "-\n", "$0.03\n", "Nvidia T4 - small\n", "4 vCPU\n", "15 GB\n", "Nvidia T4\n", "16 GB\n", "$0.40\n", "Nvidia T4 - medium\n", "8 vCPU\n", "30 GB\n", "Nvidia T4\n", "16 GB\n", "$0.60\n", "1x Nvidia L4\n", "8 vCPU\n", "30 GB\n", "Nvidia L4\n", "24 GB\n", "$0.80\n", "4x Nvidia L4\n", "48 vCPU\n", "186 GB\n", "Nvidia L4\n", "96 GB\n", "$3.80\n", "1x Nvidia L40S\n", "8 vCPU\n", "62 GB\n", "Nvidia L4\n", "48 GB\n", "$1.80\n", "4x Nvidia L40S\n", "48 vCPU\n", "382 GB\n", "Nvidia L4\n", "192 GB\n", "$8.30\n", "8x Nvidia L40S\n", "192 vCPU\n", "1534 GB\n", "Nvidia L4\n", "384 GB\n", "$23.50\n", "Nvidia A10G - small\n", "4 vCPU\n", "15 GB\n", "Nvidia A10G\n", "24 GB\n", "$1.00\n", "Nvidia A10G - large\n", "12 vCPU\n", "46 GB\n", "Nvidia A10G\n", "24 GB\n", "$1.50\n", "2x Nvidia A10G - large\n", "24 vCPU\n", "92 GB\n", "Nvidia A10G\n", "48 GB\n", "$3.00\n", "4x Nvidia A10G - large\n", "48 vCPU\n", "184 GB\n", "Nvidia A10G\n", "96 GB\n", "$5.00\n", "Nvidia A100 - large\n", "12 vCPU\n", "142 GB\n", "Nvidia A100\n", "80 GB\n", "$4.00\n", "TPU v5e 1x1\n", "22 vCPU\n", "44 GB\n", "Google TPU v5e\n", "16 GB\n", "$1.20\n", "TPU v5e 2x2\n", "110 vCPU\n", "186 GB\n", "Google TPU v5e\n", "64 GB\n", "$4.75\n", "TPU v5e 2x4\n", "220 vCPU\n", "380 GB\n", "Google TPU v5e\n", "128 GB\n", "$9.50\n", "Custom\n", "on demand\n", "on demand\n", "on demand\n", "on demand\n", "on demand\n", "Spaces Persistent Storage\n", "All Spaces get ephemeral storage for free but you can upgrade and add persistent storage at any time.\n", "Name\n", "Storage\n", "Monthly price\n", "Small\n", "20 GB\n", "$5\n", "Medium\n", "150 GB\n", "$25\n", "Large\n", "1 TB\n", "$100\n", "Building something cool as a side project? We also offer community GPU grants.\n", "Inference Endpoints\n", "Starting at $0.033/hour\n", "Inference Endpoints (dedicated) offers a secure production solution to easily deploy any ML model on dedicated\n", "\t\t\t\t\tand autoscaling infrastructure, right from the HF Hub.\n", "→\n", "Learn more\n", "CPU\n", "instances\n", "Provider\n", "Architecture\n", "vCPUs\n", "Memory\n", "Hourly rate\n", "aws\n", "Intel Sapphire Rapids\n", "1\n", "2GB\n", "$0.03\n", "2\n", "4GB\n", "$0.07\n", "4\n", "8GB\n", "$0.13\n", "8\n", "16GB\n", "$0.27\n", "16\n", "32GB\n", "$0.54\n", "azure\n", "Intel Xeon\n", "1\n", "2GB\n", "$0.06\n", "2\n", "4GB\n", "$0.12\n", "4\n", "8GB\n", "$0.24\n", "8\n", "16GB\n", "$0.48\n", "gcp\n", "Intel Sapphire Rapids\n", "1\n", "2GB\n", "$0.05\n", "2\n", "4GB\n", "$0.10\n", "4\n", "8GB\n", "$0.20\n", "8\n", "16GB\n", "$0.40\n", "Accelerator\n", "instances\n", "Provider\n", "Architecture\n", "Topology\n", "Accelerator Memory\n", "Hourly rate\n", "aws\n", "Inf2\n", "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tNeuron\n", "x1\n", "14.5GB\n", "$0.75\n", "x12\n", "760GB\n", "$12.00\n", "gcp\n", "TPU\n", "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tv5e\n", "1x1\n", "16GB\n", "$1.20\n", "2x2\n", "64GB\n", "$4.75\n", "2x4\n", "128GB\n", "$9.50\n", "GPU\n", "instances\n", "Provider\n", "Architecture\n", "GPUs\n", "GPU Memory\n", "Hourly rate\n", "aws\n", "NVIDIA T4\n", "1\n", "14GB\n", "$0.50\n", "4\n", "56GB\n", "$3.00\n", "aws\n", "NVIDIA L4\n", "1\n", "24GB\n", "$0.80\n", "4\n", "96GB\n", "$3.80\n", "aws\n", "NVIDIA L40S\n", "1\n", "48GB\n", "$1.80\n", "4\n", "192GB\n", "$8.30\n", "8\n", "384GB\n", "$23.50\n", "aws\n", "NVIDIA A10G\n", "1\n", "24GB\n", "$1.00\n", "4\n", "96GB\n", "$5.00\n", "aws\n", "NVIDIA A100\n", "1\n", "80GB\n", "$4.00\n", "2\n", "160GB\n", "$8.00\n", "4\n", "320GB\n", "$16.00\n", "8\n", "640GB\n", "$32.00\n", "gcp\n", "NVIDIA T4\n", "1\n", "16GB\n", "$0.50\n", "gcp\n", "NVIDIA L4\n", "1\n", "24GB\n", "$0.70\n", "4\n", "96GB\n", "$3.80\n", "gcp\n", "NVIDIA A100\n", "1\n", "80GB\n", "$3.60\n", "2\n", "160GB\n", "$7.20\n", "4\n", "320GB\n", "$14.40\n", "8\n", "640GB\n", "$28.80\n", "gcp\n", "NVIDIA H100\n", "1\n", "80GB\n", "$10.00\n", "2\n", "160GB\n", "$20.00\n", "4\n", "320GB\n", "$40.00\n", "8\n", "640GB\n", "$80.00\n", "Pro Account\n", "PRO\n", "A monthly subscription to access powerful features.\n", "→\n", "Get Pro\n", "($9/month)\n", "ZeroGPU\n", ": Get 5x usage quota and highest GPU queue priority\n", "Spaces Hosting\n", ": Create ZeroGPU Spaces with A100 hardware\n", "Spaces Dev Mode\n", ": Fast iterations via SSH/VS Code for Spaces\n", "Inference Providers\n", ": Get $2 included credits across all Inference Providers\n", "Dataset Viewer\n", ": Activate it on private datasets\n", "Blog Articles\n", ": Publish articles to the Hugging Face blog\n", "Social Posts\n", ": Share short updates with the community\n", "Features Preview\n", ": Get early access to upcoming\n", "\t\t\t\t\t\t\t\t\t\tfeatures\n", "PRO\n", "Badge\n", ":\n", "\t\t\t\t\t\t\t\t\t\tShow your support on your profile\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", "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", "LeRobot\n", "Accelerating LLM Inference with TGI on Intel Gaudi\n", "By\n", "baptistecolle\n", "March 28, 2025\n", "•\n", "6\n", "Community Articles\n", "view all\n", "🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?\n", "By\n", "Kseniase\n", "•\n", "11 days ago\n", "•\n", "89\n", "Open R1: Update #4\n", "By\n", "open-r1\n", "and 3 others\n", "•\n", "2 days ago\n", "•\n", "34\n", "Open R1: Update #3\n", "By\n", "open-r1\n", "and 9 others\n", "•\n", "17 days ago\n", "•\n", "274\n", "DeepSearch Using Visual RAG in Agentic Frameworks 🔎\n", "By\n", "paultltc\n", "and 1 other\n", "•\n", "7 days ago\n", "•\n", "28\n", "I Clicked “I Agree”, But What Am I Really Consenting To?\n", "By\n", "giadap\n", "•\n", "2 days ago\n", "•\n", "19\n", "Uncensor any LLM with abliteration\n", "By\n", "mlabonne\n", "•\n", "Jun 13, 2024\n", "•\n", "495\n", "Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques\n", "By\n", "jmamou\n", "and 8 others\n", "•\n", "4 days ago\n", "•\n", "15\n", "FeeL: Making Multilingual LMs Better, One Feedback Loop at a Time\n", "By\n", "borgr\n", "and 1 other\n", "•\n", "3 days ago\n", "•\n", "10\n", "DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge\n", "By\n", "NormalUhr\n", "•\n", "Feb 7\n", "•\n", "89\n", "ColPali: Efficient Document Retrieval with Vision Language Models 👀\n", "By\n", "manu\n", "•\n", "Jul 5, 2024\n", "•\n", "226\n", "KV Caching Explained: Optimizing Transformer Inference Efficiency\n", "By\n", "not-lain\n", "•\n", "Jan 30\n", "•\n", "46\n", "Introducing EuroBERT: A High-Performance Multilingual Encoder Model\n", "By\n", "EuroBERT\n", "and 3 others\n", "•\n", "18 days ago\n", "•\n", "133\n", "Understanding and Implementing the Tree of Thoughts Paradigm\n", "By\n", "sadhaklal\n", "•\n", "2 days ago\n", "•\n", "7\n", "Open-Source Handwritten Signature Detection Model\n", "By\n", "samuellimabraz\n", "•\n", "14 days ago\n", "•\n", "89\n", "makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch\n", "By\n", "AviSoori1x\n", "•\n", "May 7, 2024\n", "•\n", "70\n", "Mastering Tensor Dimensions in Transformers\n", "By\n", "not-lain\n", "•\n", "Jan 12\n", "•\n", "56\n", "PangolinGuard: Fine-Tuning ModernBERT as a Lightweight Approach to AI Guardrails\n", "By\n", "dcarpintero\n", "•\n", "5 days ago\n", "•\n", "5\n", "The Large Language Model Course\n", "By\n", "mlabonne\n", "•\n", "Jan 16\n", "•\n", "144\n", "Manus AI: The Best Autonomous AI Agent Redefining Automation and Productivity\n", "By\n", "LLMhacker\n", "•\n", "23 days ago\n", "•\n", "151\n", "mistral.rs v0.5.0\n", "By\n", "EricB\n", "•\n", "5 days ago\n", "•\n", "5\n", "Training and Finetuning Reranker Models with Sentence Transformers v4\n", "By\n", "tomaarsen\n", "March 26, 2025\n", "•\n", "60\n", "Introducing Gradio's new Dataframe!\n", "By\n", "hmb\n", "March 24, 2025\n", "•\n", "17\n", "The New and Fresh analytics in Inference Endpoints\n", "By\n", "erikkaum\n", "March 21, 2025\n", "•\n", "17\n", "Open R1: How to use OlympicCoder locally for coding?\n", "By\n", "burtenshaw\n", "March 20, 2025\n", "•\n", "52\n", "AI Policy: 🤗 Response to the White House AI Action Plan RFI\n", "By\n", "yjernite\n", "March 19, 2025\n", "•\n", "21\n", "NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets\n", "By\n", "mingyuliutw\n", "March 18, 2025\n", "guest\n", "•\n", "29\n", "Xet is on the Hub\n", "By\n", "jsulz\n", "March 18, 2025\n", "•\n", "33\n", "Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM\n", "By\n", "ariG23498\n", "March 12, 2025\n", "•\n", "352\n", "LeRobot goes to driving school: World’s largest open-source self-driving dataset\n", "By\n", "sandhawalia\n", "March 11, 2025\n", "•\n", "68\n", "LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!\n", "By\n", "medmekk\n", "March 7, 2025\n", "•\n", "45\n", "Hugging Face and JFrog partner to make AI Security more transparent\n", "By\n", "mcpotato\n", "March 4, 2025\n", "•\n", "21\n", "A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality\n", "By\n", "saurabhdash\n", "March 4, 2025\n", "guest\n", "•\n", "70\n", "Trace & Evaluate your Agent with Arize Phoenix\n", "By\n", "m-ric\n", "February 28, 2025\n", "guest\n", "•\n", "35\n", "HuggingFace, IISc partner to supercharge model building on India's diverse languages\n", "By\n", "prasantg\n", "February 27, 2025\n", "•\n", "18\n", "Previous\n", "1\n", "2\n", "3\n", "...\n", "40\n", "Next\n", "Community Articles\n", "Sort: \n", "\t\tTrending\n", "🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?\n", "By\n", "Kseniase\n", "•\n", "11 days ago\n", "•\n", "89\n", "Open R1: Update #4\n", "By\n", "open-r1\n", "and 3 others\n", "•\n", "2 days ago\n", "•\n", "34\n", "Open R1: Update #3\n", "By\n", "open-r1\n", "and 9 others\n", "•\n", "17 days ago\n", "•\n", "274\n", "DeepSearch Using Visual RAG in Agentic Frameworks 🔎\n", "By\n", "paultltc\n", "and 1 other\n", "•\n", "7 days ago\n", "•\n", "28\n", "I Clicked “I Agree”, But What Am I Really Consenting To?\n", "By\n", "giadap\n", "•\n", "2 days ago\n", "•\n", "19\n", "Uncensor any LLM with abliteration\n", "By\n", "mlabonne\n", "•\n", "Jun 13, 2024\n", "•\n", "495\n", "Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques\n", "By\n", "jmamou\n", "and 8 others\n", "•\n", "4 days ago\n", "•\n", "15\n", "FeeL: Making Multilingual LMs Better, One Feedback Loop at a Time\n", "By\n", "borgr\n", "and 1 other\n", "•\n", "3 days ago\n", "•\n", "10\n", "DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge\n", "By\n", "NormalUhr\n", "•\n", "Feb 7\n", "•\n", "89\n", "ColPali: Efficient Document Retrieval with Vision Language Models 👀\n", "By\n", "manu\n", "•\n", "Jul 5, 2024\n", "•\n", "226\n", "KV Caching Explained: Optimizing Transformer Inference Efficiency\n", "By\n", "not-lain\n", "•\n", "Jan 30\n", "•\n", "46\n", "Introducing EuroBERT: A High-Performance Multilingual Encoder Model\n", "By\n", "EuroBERT\n", "and 3 others\n", "•\n", "18 days ago\n", "•\n", "133\n", "Understanding and Implementing the Tree of Thoughts Paradigm\n", "By\n", "sadhaklal\n", "•\n", "2 days ago\n", "•\n", "7\n", "Open-Source Handwritten Signature Detection Model\n", "By\n", "samuellimabraz\n", "•\n", "14 days ago\n", "•\n", "89\n", "makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch\n", "By\n", "AviSoori1x\n", "•\n", "May 7, 2024\n", "•\n", "70\n", "Mastering Tensor Dimensions in Transformers\n", "By\n", "not-lain\n", "•\n", "Jan 12\n", "•\n", "56\n", "PangolinGuard: Fine-Tuning ModernBERT as a Lightweight Approach to AI Guardrails\n", "By\n", "dcarpintero\n", "•\n", "5 days ago\n", "•\n", "5\n", "The Large Language Model Course\n", "By\n", "mlabonne\n", "•\n", "Jan 16\n", "•\n", "144\n", "Manus AI: The Best Autonomous AI Agent Redefining Automation and Productivity\n", "By\n", "LLMhacker\n", "•\n", "23 days ago\n", "•\n", "151\n", "mistral.rs v0.5.0\n", "By\n", "EricB\n", "•\n", "5 days ago\n", "•\n", "5\n", "View all\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", "models page\n", "Webpage Title:\n", "Models - 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", "Edit Models filters\n", "Tasks\n", "Libraries\n", "Datasets\n", "Languages\n", "Licenses\n", "Other\n", "Multimodal\n", "Audio-Text-to-Text\n", "Image-Text-to-Text\n", "Visual Question Answering\n", "Document Question Answering\n", "Video-Text-to-Text\n", "Visual Document Retrieval\n", "Any-to-Any\n", "Computer Vision\n", "Depth Estimation\n", "Image Classification\n", "Object Detection\n", "Image Segmentation\n", "Text-to-Image\n", "Image-to-Text\n", "Image-to-Image\n", "Image-to-Video\n", "Unconditional Image Generation\n", "Video Classification\n", "Text-to-Video\n", "Zero-Shot Image Classification\n", "Mask Generation\n", "Zero-Shot Object Detection\n", "Text-to-3D\n", "Image-to-3D\n", "Image Feature Extraction\n", "Keypoint Detection\n", "Natural Language Processing\n", "Text Classification\n", "Token Classification\n", "Table Question Answering\n", "Question Answering\n", "Zero-Shot Classification\n", "Translation\n", "Summarization\n", "Feature Extraction\n", "Text Generation\n", "Text2Text Generation\n", "Fill-Mask\n", "Sentence Similarity\n", "Text Ranking\n", "Audio\n", "Text-to-Speech\n", "Text-to-Audio\n", "Automatic Speech Recognition\n", "Audio-to-Audio\n", "Audio Classification\n", "Voice Activity Detection\n", "Tabular\n", "Tabular Classification\n", "Tabular Regression\n", "Time Series Forecasting\n", "Reinforcement Learning\n", "Reinforcement Learning\n", "Robotics\n", "Other\n", "Graph Machine Learning\n", "Apply filters\n", "Models\n", "Full-text search\n", "Add filters\n", "Sort: \n", "\t\tTrending\n", "deepseek-ai/DeepSeek-V3-0324\n", "Text Generation\n", "•\n", "Updated\n", "1 day ago\n", "•\n", "47.6k\n", "•\n", "•\n", "1.91k\n", "Qwen/Qwen2.5-Omni-7B\n", "Any-to-Any\n", "•\n", "Updated\n", "about 2 hours ago\n", "•\n", "16.3k\n", "•\n", "712\n", "manycore-research/SpatialLM-Llama-1B\n", "Text Generation\n", "•\n", "Updated\n", "7 days ago\n", "•\n", "6.85k\n", "•\n", "760\n", "ByteDance/InfiniteYou\n", "Text-to-Image\n", "•\n", "Updated\n", "3 days ago\n", "•\n", "448\n", "ds4sd/SmolDocling-256M-preview\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "5 days ago\n", "•\n", "44.8k\n", "•\n", "1.01k\n", "sesame/csm-1b\n", "Text-to-Speech\n", "•\n", "Updated\n", "12 days ago\n", "•\n", "53.7k\n", "•\n", "•\n", "1.71k\n", "starvector/starvector-8b-im2svg\n", "Text Generation\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "6.24k\n", "•\n", "354\n", "Qwen/Qwen2.5-VL-32B-Instruct\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "2 days ago\n", "•\n", "72.7k\n", "•\n", "246\n", "mistralai/Mistral-Small-3.1-24B-Instruct-2503\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "6 days ago\n", "•\n", "102k\n", "•\n", "1.01k\n", "deepseek-ai/DeepSeek-R1\n", "Text Generation\n", "•\n", "Updated\n", "1 day ago\n", "•\n", "1.42M\n", "•\n", "•\n", "11.7k\n", "canopylabs/orpheus-3b-0.1-ft\n", "Text-to-Speech\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "36.1k\n", "•\n", "418\n", "tencent/Hunyuan3D-2mv\n", "Image-to-3D\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "7.13k\n", "•\n", "348\n", "Qwen/QwQ-32B\n", "Text Generation\n", "•\n", "Updated\n", "17 days ago\n", "•\n", "688k\n", "•\n", "•\n", "2.56k\n", "SUFE-AIFLM-Lab/Fin-R1\n", "Updated\n", "8 days ago\n", "•\n", "893\n", "•\n", "155\n", "google/gemma-3-27b-it\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "7 days ago\n", "•\n", "901k\n", "•\n", "•\n", "1.01k\n", "black-forest-labs/FLUX.1-dev\n", "Text-to-Image\n", "•\n", "Updated\n", "Aug 16, 2024\n", "•\n", "2.8M\n", "•\n", "•\n", "9.57k\n", "starvector/starvector-1b-im2svg\n", "Text Generation\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "11.9k\n", "•\n", "133\n", "nvidia/canary-1b-flash\n", "Automatic Speech Recognition\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "8.64k\n", "•\n", "156\n", "unsloth/DeepSeek-V3-0324-GGUF\n", "Text Generation\n", "•\n", "Updated\n", "2 days ago\n", "•\n", "87.7k\n", "•\n", "88\n", "deepseek-ai/DeepSeek-V3\n", "Text Generation\n", "•\n", "Updated\n", "1 day ago\n", "•\n", "1.42M\n", "•\n", "•\n", "3.74k\n", "teapotai/teapotllm\n", "Text2Text Generation\n", "•\n", "Updated\n", "2 days ago\n", "•\n", "5.03k\n", "•\n", "•\n", "83\n", "hexgrad/Kokoro-82M\n", "Text-to-Speech\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "1.67M\n", "•\n", "3.83k\n", "nvidia/GR00T-N1-2B\n", "Robotics\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "1.68k\n", "•\n", "247\n", "VIDraft/Gemma-3-R1984-27B\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "about 24 hours ago\n", "•\n", "186\n", "•\n", "74\n", "google/gemma-3-4b-it\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "7 days ago\n", "•\n", "326k\n", "•\n", "357\n", "microsoft/Phi-4-multimodal-instruct\n", "Automatic Speech Recognition\n", "•\n", "Updated\n", "about 21 hours ago\n", "•\n", "826k\n", "•\n", "1.25k\n", "Qwen/Qwen2.5-VL-7B-Instruct\n", "Image-Text-to-Text\n", "•\n", "Updated\n", "6 days ago\n", "•\n", "3.34M\n", "•\n", "•\n", "751\n", "stabilityai/stable-virtual-camera\n", "Image-to-Video\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "8.12k\n", "•\n", "147\n", "stabilityai/stable-diffusion-3.5-large\n", "Text-to-Image\n", "•\n", "Updated\n", "Oct 22, 2024\n", "•\n", "146k\n", "•\n", "•\n", "2.57k\n", "SicariusSicariiStuff/X-Ray_Alpha\n", "Updated\n", "3 days ago\n", "•\n", "203\n", "•\n", "48\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", "datasets 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", "Edit Datasets filters\n", "Main\n", "Tasks\n", "Libraries\n", "Languages\n", "Licenses\n", "Other\n", "Modalities\n", "3D\n", "Audio\n", "Geospatial\n", "Image\n", "Tabular\n", "Text\n", "Time-series\n", "Video\n", "Size\n", "\t\t\t(rows)\n", "Reset Size\n", "< 1K\n", "> 1T\n", "Format\n", "json\n", "csv\n", "parquet\n", "imagefolder\n", "soundfolder\n", "webdataset\n", "text\n", "arrow\n", "Apply filters\n", "Datasets\n", "341,954\n", "Full-text search\n", "Add filters\n", "Sort: \n", "\t\tTrending\n", "nvidia/Llama-Nemotron-Post-Training-Dataset-v1\n", "Viewer\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "15.2M\n", "•\n", "7.64k\n", "•\n", "258\n", "glaiveai/reasoning-v1-20m\n", "Viewer\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "22.2M\n", "•\n", "6.31k\n", "•\n", "119\n", "FreedomIntelligence/medical-o1-reasoning-SFT\n", "Viewer\n", "•\n", "Updated\n", "Feb 22\n", "•\n", "50.1k\n", "•\n", "26.3k\n", "•\n", "568\n", "a-m-team/AM-DeepSeek-R1-Distilled-1.4M\n", "Preview\n", "•\n", "Updated\n", "about 3 hours ago\n", "•\n", "2.98k\n", "•\n", "72\n", "facebook/collaborative_agent_bench\n", "Preview\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "89\n", "•\n", "47\n", "PixelAI-Team/TalkBody4D\n", "Viewer\n", "•\n", "Updated\n", "3 days ago\n", "•\n", "1.05M\n", "•\n", "60\n", "•\n", "40\n", "nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim\n", "Updated\n", "7 days ago\n", "•\n", "26.9k\n", "•\n", "88\n", "manycore-research/SpatialLM-Testset\n", "Viewer\n", "•\n", "Updated\n", "9 days ago\n", "•\n", "107\n", "•\n", "6.98k\n", "•\n", "43\n", "Congliu/Chinese-DeepSeek-R1-Distill-data-110k\n", "Viewer\n", "•\n", "Updated\n", "Feb 21\n", "•\n", "110k\n", "•\n", "6.58k\n", "•\n", "597\n", "Anthropic/EconomicIndex\n", "Viewer\n", "•\n", "Updated\n", "about 19 hours ago\n", "•\n", "3.36k\n", "•\n", "2.56k\n", "•\n", "224\n", "open-r1/codeforces-cots\n", "Viewer\n", "•\n", "Updated\n", "about 5 hours ago\n", "•\n", "254k\n", "•\n", "7.78k\n", "•\n", "114\n", "Intelligent-Internet/II-Thought-RL-v0\n", "Viewer\n", "•\n", "Updated\n", "about 2 hours ago\n", "•\n", "342k\n", "•\n", "1.19k\n", "•\n", "26\n", "facebook/natural_reasoning\n", "Viewer\n", "•\n", "Updated\n", "Feb 21\n", "•\n", "1.15M\n", "•\n", "13.6k\n", "•\n", "464\n", "Conard/fortune-telling\n", "Viewer\n", "•\n", "Updated\n", "Feb 17\n", "•\n", "207\n", "•\n", "6.17k\n", "•\n", "105\n", "HuggingFaceFW/fineweb\n", "Viewer\n", "•\n", "Updated\n", "Jan 31\n", "•\n", "25B\n", "•\n", "228k\n", "•\n", "2.07k\n", "sychonix/emotion\n", "Viewer\n", "•\n", "Updated\n", "2 days ago\n", "•\n", "20k\n", "•\n", "114\n", "•\n", "17\n", "openai/gsm8k\n", "Viewer\n", "•\n", "Updated\n", "Jan 4, 2024\n", "•\n", "17.6k\n", "•\n", "334k\n", "•\n", "664\n", "open-thoughts/OpenThoughts-114k\n", "Viewer\n", "•\n", "Updated\n", "Feb 20\n", "•\n", "228k\n", "•\n", "33.5k\n", "•\n", "672\n", "zhang0jhon/Aesthetic-4K\n", "Viewer\n", "•\n", "Updated\n", "4 days ago\n", "•\n", "2.7k\n", "•\n", "1.38k\n", "•\n", "16\n", "Rapidata/OpenAI-4o_t2i_human_preference\n", "Viewer\n", "•\n", "Updated\n", "about 3 hours ago\n", "•\n", "13k\n", "•\n", "257\n", "•\n", "15\n", "fka/awesome-chatgpt-prompts\n", "Viewer\n", "•\n", "Updated\n", "Jan 6\n", "•\n", "203\n", "•\n", "12.1k\n", "•\n", "7.65k\n", "starvector/svg-stack\n", "Viewer\n", "•\n", "Updated\n", "Jan 10\n", "•\n", "2.28M\n", "•\n", "1.13k\n", "•\n", "16\n", "BytedTsinghua-SIA/DAPO-Math-17k\n", "Viewer\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "1.79M\n", "•\n", "2.83k\n", "•\n", "45\n", "nvidia/HelpSteer3\n", "Viewer\n", "•\n", "Updated\n", "10 days ago\n", "•\n", "99k\n", "•\n", "897\n", "•\n", "32\n", "MrDragonFox/Elise\n", "Viewer\n", "•\n", "Updated\n", "1 day ago\n", "•\n", "1.2k\n", "•\n", "204\n", "•\n", "13\n", "mlabonne/FineTome-100k\n", "Viewer\n", "•\n", "Updated\n", "Jul 29, 2024\n", "•\n", "100k\n", "•\n", "19.2k\n", "•\n", "192\n", "MaziyarPanahi/Llama-Nemotron-Post-Training-Dataset-v1-ShareGPT\n", "Viewer\n", "•\n", "Updated\n", "5 days ago\n", "•\n", "30.2M\n", "•\n", "924\n", "•\n", "28\n", "fibonacciai/shahname\n", "Viewer\n", "•\n", "Updated\n", "4 days ago\n", "•\n", "99.2k\n", "•\n", "35\n", "•\n", "12\n", "fibonacciai/Persian-Wikipedia-QA\n", "Viewer\n", "•\n", "Updated\n", "4 days ago\n", "•\n", "26.5k\n", "•\n", "34\n", "•\n", "11\n", "dair-ai/emotion\n", "Viewer\n", "•\n", "Updated\n", "Aug 8, 2024\n", "•\n", "437k\n", "•\n", "15.9k\n", "•\n", "342\n", "Previous\n", "1\n", "2\n", "3\n", "...\n", "100\n", "Next\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", "spaces page\n", "Webpage Title:\n", "Spaces - 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", "Spaces\n", "·\n", "The AI App Directory\n", "New Space\n", "What is Spaces?\n", "Image Generation\n", "Video Generation\n", "Text Generation\n", "Language Translation\n", "Speech Synthesis\n", "3D Modeling\n", "Object Detection\n", "Text Analysis\n", "Image Editing\n", "Code Generation\n", "Question Answering\n", "Data Visualization\n", "Voice Cloning\n", "Background Removal\n", "Image Upscaling\n", "OCR\n", "Document Analysis\n", "Visual QA\n", "Image Captioning\n", "Chatbots\n", "Sentiment Analysis\n", "Text Summarization\n", "Music Generation\n", "Medical Imaging\n", "Financial Analysis\n", "Game AI\n", "Model Benchmarking\n", "Fine Tuning Tools\n", "Dataset Creation\n", "Pose Estimation\n", "Face Recognition\n", "Anomaly Detection\n", "Recommendation Systems\n", "Character Animation\n", "Style Transfer\n", "Image\n", "Spaces of the week\n", "24 Mar 2025\n", "Sort: \n", "\t\tRelevance\n", "Running\n", "on\n", "L40S\n", "115\n", "Cube3d Interactive\n", "🌍\n", "interactive demo for cube 3d model\n", "Roblox\n", "7 days ago\n", "Running\n", "on\n", "Zero\n", "493\n", "InfiniteYou-FLUX\n", "📸\n", "Flexible Photo Recrafting While Preserving Your Identity\n", "ByteDance\n", "3 days ago\n", "Running\n", "on\n", "Zero\n", "201\n", "SmolDocling\n", "🦆\n", "Convert images and text to document formats\n", "ds4sd\n", "10 days ago\n", "Running\n", "167\n", "Hunyuan T1\n", "💬\n", "Hunyuan T1模型体验\n", "tencent\n", "6 days ago\n", "Running\n", "331\n", "Gemini Co-Drawing\n", "✏\n", "Gemini 2.0 native image generation co-doodling\n", "Trudy\n", "8 days ago\n", "Running\n", "62\n", "Follow History\n", "🔥\n", "Track history of Follows of organizations and users on HF\n", "julien-c\n", "9 days ago\n", "Running\n", "on\n", "Zero\n", "108\n", "Orpheus TTS\n", "🚀\n", "Try Orpheus TTS here\n", "MohamedRashad\n", "2 days ago\n", "All running apps, trending first\n", "Running\n", "on\n", "Zero\n", "493\n", "InfiniteYou-FLUX\n", "📸\n", "Flexible Photo Recrafting While Preserving Your Identity\n", "ByteDance\n", "3 days ago\n", "Running\n", "on\n", "Zero\n", "211\n", "LHM\n", "⚡\n", "Large Animatable Human Model\n", "3DAIGC\n", "1 day ago\n", "Running\n", "331\n", "Gemini Co-Drawing\n", "✏\n", "Gemini 2.0 native image generation co-doodling\n", "Trudy\n", "8 days ago\n", "Running\n", "167\n", "Hunyuan T1\n", "💬\n", "Hunyuan T1模型体验\n", "tencent\n", "6 days ago\n", "Running\n", "on\n", "L40S\n", "328\n", "Stable Virtual Camera\n", "⚡\n", "Generate virtual camera views from input images\n", "stabilityai\n", "4 days ago\n", "Running\n", "141\n", "starvector-1b-im2svg\n", "📈\n", "Convert images and text into scalable vector graphics (SVG) code\n", "starvector\n", "3 days ago\n", "Running\n", "139\n", "Qwen2.5 Omni 7B Demo\n", "🏆\n", "Submit media inputs to generate text and speech responses\n", "Qwen\n", "1 day ago\n", "Running\n", "on\n", "Zero\n", "4.42k\n", "TRELLIS\n", "🏢\n", "Scalable and Versatile 3D Generation from images\n", "JeffreyXiang\n", "Dec 18, 2024\n", "Running\n", "on\n", "Zero\n", "683\n", "Sesame CSM\n", "🌱\n", "Conversational speech generation\n", "sesame\n", "3 days ago\n", "Running\n", "113\n", "Deepseek v3-0324 Research\n", "🏃\n", "Deepseek v3-0324 + Real Time Deep Research\n", "openfree\n", "about 24 hours ago\n", "Running\n", "on\n", "Zero\n", "7.98k\n", "FLUX.1 [dev]\n", "🖥\n", "Generate images from text prompts\n", "black-forest-labs\n", "Oct 9, 2024\n", "Running\n", "on\n", "L40S\n", "115\n", "Cube3d Interactive\n", "🌍\n", "interactive demo for cube 3d model\n", "Roblox\n", "7 days ago\n", "Running\n", "on\n", "CPU Upgrade\n", "8.09k\n", "Kolors Virtual Try-On\n", "👕\n", "Overlay garment on person image\n", "Kwai-Kolors\n", "Sep 18, 2024\n", "Running\n", "on\n", "Zero\n", "1.2k\n", "LuminaBrush\n", "📈\n", "Execute custom code from environment variable\n", "lllyasviel\n", "Dec 21, 2024\n", "Running\n", "on\n", "Zero\n", "2.14k\n", "Hunyuan3D-2.0\n", "🌍\n", "Text-to-3D and Image-to-3D Generation\n", "tencent\n", "6 days ago\n", "Running\n", "on\n", "L4\n", "269\n", "Thera Arbitrary-Scale Super-Resolution\n", "🔥\n", "Enhance image quality with real-time super-resolution\n", "prs-eth\n", "5 days ago\n", "Running\n", "on\n", "Zero\n", "3.14k\n", "IC Light V2\n", "📈\n", "Execute code provided in environment variable\n", "lllyasviel\n", "Oct 26, 2024\n", "Running\n", "on\n", "Zero\n", "108\n", "Orpheus TTS\n", "🚀\n", "Try Orpheus TTS here\n", "MohamedRashad\n", "2 days ago\n", "Running\n", "162\n", "FLUX - EVERY TEXT Imaginator\n", "🖼\n", "FLUX Multilingual Text-Driven Image Generation and Editing\n", "ginigen\n", "3 days ago\n", "Running\n", "on\n", "CPU Upgrade\n", "5.23k\n", "MTEB Leaderboard\n", "🥇\n", "Embedding Leaderboard\n", "mteb\n", "about 6 hours ago\n", "Running\n", "70\n", "Deepseek v3-0324 Research korea\n", "💬\n", "Deepseek v3-0324 + Real Time Deep Research\n", "openfree\n", "3 days ago\n", "Running\n", "on\n", "A100\n", "67\n", "Gemma-3-R1984-27B\n", "🔥\n", "Reasoning + Multimodal + VLM + Deep Research + Agent\n", "VIDraft\n", "about 5 hours ago\n", "Running\n", "on\n", "Zero\n", "201\n", "SmolDocling\n", "🦆\n", "Convert images and text to document formats\n", "ds4sd\n", "10 days ago\n", "Running\n", "on\n", "Zero\n", "191\n", "Hunyuan3D 2mv Turbo\n", "🌍\n", "MultiImages-to-3D Generation\n", "tencent\n", "9 days ago\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" ] } ], "source": [ "print(get_all_details(\"https://huggingface.co\"))" ] }, { "cell_type": "code", "execution_count": 21, "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": 22, "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": 23, "id": "cd909e0b-1312-4ce2-a553-821e795d7572", "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': 'company page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'discussion forum', 'url': 'https://discuss.huggingface.co'}, {'type': 'social media', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn profile', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" ] }, { "data": { "text/plain": [ "\"You are looking at a company called: HuggingFace\\nHere are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\nLanding page:\\nWebpage Title:\\nHugging Face – The AI community building the future.\\nWebpage Contents:\\nHugging Face\\nModels\\nDatasets\\nSpaces\\nPosts\\nDocs\\nEnterprise\\nPricing\\nLog In\\nSign Up\\nThe AI community building the future.\\nThe platform where the machine learning community collaborates on models, datasets, and applications.\\nExplore AI Apps\\nor\\nBrowse 1M+ models\\nTrending on\\nthis week\\nModels\\ndeepseek-ai/DeepSeek-V3-0324\\nUpdated\\n1 day ago\\n•\\n47.6k\\n•\\n1.91k\\nQwen/Qwen2.5-Omni-7B\\nUpdated\\nabout 2 hours ago\\n•\\n16.3k\\n•\\n712\\nmanycore-research/SpatialLM-Llama-1B\\nUpdated\\n7 days ago\\n•\\n6.85k\\n•\\n760\\nByteDance/InfiniteYou\\nUpdated\\n3 days ago\\n•\\n448\\nds4sd/SmolDocling-256M-preview\\nUpdated\\n5 days ago\\n•\\n44.8k\\n•\\n1.01k\\nBrowse 1M+ models\\nSpaces\\nRunning\\non\\nZero\\n493\\n493\\nInfiniteYou-FLUX\\n📸\\nFlexible Photo Recrafting While Preserving Your Identity\\nRunning\\non\\nZero\\n211\\n211\\nLHM\\n⚡\\nLarge Animatable Human Model\\nRunning\\n331\\n331\\nGemini Co-Drawing\\n✏\\nGemini 2.0 native image generation co-doodling\\nRunning\\n167\\n167\\nHunyuan T1\\n💬\\nHunyuan T1模型体验\\nRunning\\non\\nL40S\\n328\\n328\\nStable Virtual Camera\\n⚡\\nGenerate virtual camera views from input images\\nBrowse 400k+ applications\\nDatasets\\nnvidia/Llama-Nemotron-Post-Training-Dataset-v1\\nUpdated\\n10 days ago\\n•\\n7.64k\\n•\\n258\\nglaiveai/reasoning-v1-20m\\nUpdated\\n9 days ago\\n•\\n6.31k\\n•\\n119\\nFreedomIntelligence/medical-o1-reasoning-SFT\\nUpdated\\nFeb 22\\n•\\n26.3k\\n•\\n568\\na-m-team/AM-DeepSeek-R1-Distilled-1.4M\\nUpdated\\nabout 3 hours ago\\n•\\n2.98k\\n•\\n72\\nfacebook/collaborative_agent_bench\\nUpdated\\n9 days ago\\n•\\n89\\n•\\n47\\nBrowse 250k+ datasets\\nThe Home of Machine Learning\\nCreate, discover and collaborate on ML better.\\nThe collaboration platform\\nHost and collaborate on unlimited public models, datasets and applications.\\nMove faster\\nWith the HF Open source stack.\\nExplore all modalities\\nText, image, video, audio or even 3D.\\nBuild your portfolio\\nShare your work with the world and build your ML profile.\\nSign Up\\nAccelerate your ML\\nWe provide paid Compute and Enterprise solutions.\\nCompute\\nDeploy on optimized\\nInference Endpoints\\nor update your\\nSpaces applications\\nto a GPU in a few clicks.\\nView pricing\\nStarting at $0.60/hour for GPU\\nEnterprise\\nGive your team the most advanced platform to build AI with enterprise-grade security, access controls and\\n\\t\\t\\tdedicated support.\\nGetting started\\nStarting at $20/user/month\\nSingle Sign-On\\nRegions\\nPriority Support\\nAudit Logs\\nResource Groups\\nPrivate Datasets Viewer\\nMore than 50,000 organizations are using Hugging Face\\nAi2\\nEnterprise\\nnon-profit\\n•\\n396 models\\n•\\n2.97k followers\\nAI at Meta\\nEnterprise\\ncompany\\n•\\n2.07k models\\n•\\n5.28k followers\\nAmazon\\ncompany\\n•\\n10 models\\n•\\n2.91k followers\\nGoogle\\ncompany\\n•\\n974 models\\n•\\n10.6k followers\\nIntel\\ncompany\\n•\\n219 models\\n•\\n2.37k followers\\nMicrosoft\\ncompany\\n•\\n365 models\\n•\\n10.7k followers\\nGrammarly\\nEnterprise\\ncompany\\n•\\n10 models\\n•\\n146 followers\\nWriter\\nEnterprise\\ncompany\\n•\\n21 models\\n•\\n253 followers\\nOur Open Source\\nWe are building the foundation of ML tooling with the community.\\nTransformers\\n142,079\\nState-of-the-art ML for PyTorch, TensorFlow, JAX\\nDiffusers\\n28,301\\nState-of-the-art Diffusion models in PyTorch\\nSafetensors\\n3,189\\nSafe way to store/distribute neural network weights\\nHub Python Library\\n2,471\\nPython client to interact with the Hugging Face Hub\\nTokenizers\\n9,538\\nFast tokenizers optimized for research & production\\nTRL\\n12,895\\nTrain transformers LMs with reinforcement learning\\nTransformers.js\\n13,312\\nState-of-the-art ML running directly in your browser\\nsmolagents\\n15,929\\nSmol library to build great agents in Python\\nPEFT\\n17,930\\nParameter-efficient finetuning for large language models\\nDatasets\\n19,892\\nAccess & share datasets for any ML tasks\\nText Generation Inference\\n9,938\\nServe language models with TGI optimized toolkit\\nAccelerate\\n8,544\\nTrain PyTorch models with multi-GPU, TPU, mixed precision\\nSystem theme\\nWebsite\\nModels\\nDatasets\\nSpaces\\nTasks\\nInference Endpoints\\nHuggingChat\\nCompany\\nAbout\\nBrand assets\\nTerms of service\\nPrivacy\\nJobs\\nPress\\nResources\\nLearn\\nDocumentation\\nBlog\\nForum\\nService Status\\nSocial\\nGitHub\\nTwitter\\nLinkedIn\\nDiscord\\n\\n\\n\\nabout page\\nWebpage Title:\\nabout (Sergei)\\nWebpage Contents:\\nHugging Face\\nModels\\nDatasets\\nSpaces\\nPosts\\nDocs\\nEnterprise\\nPricing\\nLog In\\nSign Up\\nSergei\\nabout\\nFollow\\nAlbertRuan's profile picture\\nselvivincent's profile picture\\nRenumathi's profile picture\\n4\\n\\t\\t\\t\\t\\tfollowers\\n·\\n0 following\\nAI & ML interests\\nNone yet\\nOrganizations\\nNone yet\\nmodels\\nNone public yet\\ndatasets\\nNone public yet\\nSystem theme\\nCompany\\nTOS\\nPrivacy\\nAbout\\nJobs\\nWebsite\\nModels\\nDatasets\\nSpaces\\nPricing\\nDocs\\n\\n\\n\\ncareers page\\nWebpage Title:\\nHugging Face - Current Openings\\nWebpage Contents:\\n\\n\\n\\n\\ncompany page\\nWebpage Title:\\nEnterprise Hub - Hugging Face\\nWebpage Contents:\\nHugging Face\\nModels\\nDatasets\\nSpaces\\nPosts\\nDocs\\nEnterprise\\nPricing\\nLog In\\nSign Up\\nEnterprise Hub\\nEnterprise-ready version of the world’s leading AI platform\\nSubscribe to\\nEnterpris\"" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "get_brochure_user_prompt(\"HuggingFace\", \"https://huggingface.co\")" ] }, { "cell_type": "code", "execution_count": 24, "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": 25, "id": "e093444a-9407-42ae-924a-145730591a39", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'company page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" ] }, { "data": { "text/markdown": [ "# Hugging Face Brochure\n", "\n", "## Welcome to Hugging Face\n", "\n", "**Hugging Face** is at the forefront of the artificial intelligence and machine learning revolution, dedicated to building a collaborative community that shapes the future of AI. Our platform is where the machine learning community connects, shares, and innovates—whether it's models, datasets, or applications.\n", "\n", "### Why Choose Hugging Face?\n", "\n", "- **Extensive Model Library:** Explore and utilize over **1 million% models** across various modalities including text, image, video, audio, and 3D.\n", "- **Datasets for All:** Access and share more than **250,000 datasets** for your machine learning tasks.\n", "- **Dedicated Spaces:** Run and showcase **400,000+ applications** in our dedicated spaces.\n", "- **Open Source Collaboration:** Contribute to cutting-edge tooling and libraries like Transformers, Diffusers, and more within our vibrant community.\n", "\n", "### Who We Serve\n", "\n", "Hugging Face is trusted by more than **50,000 organizations**, including industry leaders such as:\n", "- **Google**\n", "- **Microsoft**\n", "- **Amazon**\n", "- **Meta**\n", "- **Intel**\n", "- **Grammarly**\n", "\n", "### Our Company Culture\n", "\n", "At Hugging Face, we foster a **collaborative and inclusive environment** where innovation thrives. Our team is not just about technology; it's about people coming together to share knowledge, support one another, and create meaningful solutions. We promote continuous learning and encourage our team members to contribute ideas that drive the company forward.\n", "\n", "### Careers & Opportunities\n", "\n", "We are always looking for talent! Join us and become a part of the future of AI. **Explore career opportunities** at Hugging Face to find positions that align with your passion and skills. Whether you're an engineer, researcher, or enthusiast, we welcome diverse skills and perspectives to help shape the future of AI together.\n", "\n", "**Interested in joining us? [Find out more about current job openings.](#)**\n", "\n", "### Join the AI Revolution\n", "\n", "Ready to be part of something bigger? **[Sign up now](#)** to start exploring, collaborating, and innovating. Together, let's build the future of AI!\n", "\n", "--- \n", "\n", "For more information, visit us at [huggingface.co](https://huggingface.co). Follow us on social media; we're active on GitHub, Twitter, LinkedIn, and more!" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "create_brochure(\"HuggingFace\", \"https://huggingface.co\")" ] }, { "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": 26, "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": 27, "id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'community page', 'url': 'https://discuss.huggingface.co'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" ] }, { "data": { "text/markdown": [ "# Hugging Face Brochure\n", "\n", "---\n", "\n", "## Company Overview\n", "\n", "**Hugging Face** is the leading platform for the AI community focused on machine learning collaboration. With over one million models available for exploration, Hugging Face serves as a pivotal resource where individuals and organizations can create, discover, and work together on innovative ML projects. The company empowers developers, researchers, and enterprises to accelerate their machine learning endeavors through tools, datasets, and applications designed for a collaborative experience.\n", "\n", "---\n", "\n", "## Our Offerings\n", "\n", "- **Models**: Access a wealth of machine learning models spanning various applications from text to images and beyond.\n", "- **Datasets**: Browse over 250,000 datasets for all your machine learning needs.\n", "- **Spaces**: Explore custom applications powered by Hugging Face technology that can run seamlessly on the platform.\n", "- **Enterprise Solutions**: Optimal for businesses looking for enhanced security, dedicated support, and private resource management, tailored to facilitate advanced AI work.\n", "\n", "---\n", "\n", "## Who We Serve\n", "\n", "Hugging Face caters to a diverse range of customers, including over **50,000 organizations** like:\n", "\n", "- **Amazon**\n", "- **Google**\n", "- **Meta**\n", "- **Microsoft**\n", "\n", "Our offerings are utilized by non-profits, large enterprises, and individual developers, all drawn to our open-source philosophy and commitment to community collaboration.\n", "\n", "---\n", "\n", "## Company Culture\n", "\n", "At Hugging Face, we believe in **community-driven development**, where everyone contributes to building the future of AI. Our culture emphasizes inclusivity, innovation, and collaboration. We encourage team members to share their ideas and projects, fostering an environment where creativity flourishes.\n", "\n", "---\n", "\n", "## Careers at Hugging Face\n", "\n", "We are always on the lookout for passionate individuals to join our team. Working at Hugging Face offers the opportunity to be part of a pioneering community that is shaping the AI landscape. \n", "\n", "**Why Work with Us?**\n", "- Engage in cutting-edge AI research and development.\n", "- Collaborate with top industry experts.\n", "- Contribute to open-source projects impacting the global AI community.\n", "\n", "**Open Positions:** Explore current job openings on our [Careers Page](https://huggingface.co/jobs).\n", "\n", "---\n", "\n", "## Join Us\n", "\n", "Are you ready to be part of the AI revolution? Whether you're an individual looking to enhance your ML skills, an organization seeking enterprise solutions, or a potential recruit desiring a dynamic career, *Hugging Face* is your gateway to the future of AI.\n", "\n", "**Explore more at:** [Hugging Face Website](https://huggingface.co)\n", "\n", "---\n", "\n", "Together, let’s build the future of AI!" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" ] }, { "cell_type": "code", "execution_count": null, "id": "fdb3f8d8-a3eb-41c8-b1aa-9f60686a653b", "metadata": {}, "outputs": [], "source": [ "# Try changing the system prompt to the humorous version when you make the Brochure for Hugging Face:\n", "\n", "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" ] }, { "cell_type": "markdown", "id": "a27bf9e0-665f-4645-b66b-9725e2a959b5", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Business applications

\n", " In this exercise we extended the Day 1 code to make multiple LLM calls, and generate a document.\n", "\n", "This is perhaps the first example of Agentic AI design patterns, as we combined multiple calls to LLMs. This will feature more in Week 2, and then we will return to Agentic AI in a big way in Week 8 when we build a fully autonomous Agent solution.\n", "\n", "Generating content in this way is one of the very most common Use Cases. As with summarization, this can be applied to any business vertical. Write marketing content, generate a product tutorial from a spec, create personalized email content, and so much more. Explore how you can apply content generation to your business, and try making yourself a proof-of-concept prototype. See what other students have done in the community-contributions folder -- so many valuable projects -- it's wild!\n", "
" ] }, { "cell_type": "markdown", "id": "14b2454b-8ef8-4b5c-b928-053a15e0d553", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Before you move to Week 2 (which is tons of fun)

\n", " Please see the week1 EXERCISE notebook for your challenge for the end of week 1. This will give you some essential practice working with Frontier APIs, and prepare you well for Week 2.\n", "
" ] }, { "cell_type": "markdown", "id": "17b64f0f-7d33-4493-985a-033d06e8db08", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

A reminder on 3 useful resources

\n", " 1. The resources for the course are available here.
\n", " 2. I'm on LinkedIn here and I love connecting with people taking the course!
\n", " 3. I'm trying out X/Twitter and I'm at @edwarddonner and hoping people will teach me how it's done.. \n", "
\n", "
" ] }, { "cell_type": "markdown", "id": "6f48e42e-fa7a-495f-a5d4-26bfc24d60b6", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Finally! I have a special request for you

\n", " \n", " My editor tells me that it makes a MASSIVE difference when students rate this course on Udemy - it's one of the main ways that Udemy decides whether to show it to others. If you're able to take a minute to rate this, I'd be so very grateful! And regardless - always please reach out to me at ed@edwarddonner.com if I can help at any point.\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": null, "id": "b8d3e1a1-ba54-4907-97c5-30f89a24775b", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "llms", "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": "3.11.11" } }, "nbformat": 4, "nbformat_minor": 5 }