From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
158 lines
7.0 KiB
158 lines
7.0 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 9, |
|
"id": "a767b6bc-65fe-42b2-988f-efd54125114f", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"```markdown\n", |
|
"# Summary of \"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning\"\n", |
|
"\n", |
|
"## Overview\n", |
|
"The paper introduces **DeepSeek-R1**, a first-generation reasoning model developed by DeepSeek-AI. The model is designed to enhance reasoning capabilities in large language models (LLMs) using reinforcement learning (RL). Two versions are presented:\n", |
|
"- **DeepSeek-R1-Zero**: A model trained via large-scale RL without supervised fine-tuning (SFT), showcasing strong reasoning abilities but facing challenges like poor readability and language mixing.\n", |
|
"- **DeepSeek-R1**: An improved version incorporating multi-stage training and cold-start data before RL, achieving performance comparable to OpenAI's models on reasoning tasks.\n", |
|
"\n", |
|
"## Key Contributions\n", |
|
"- Open-sourcing of **DeepSeek-R1-Zero**, **DeepSeek-R1**, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama architectures.\n", |
|
"- The models are made available to support the research community.\n", |
|
"\n", |
|
"## Community Engagement\n", |
|
"- The paper has been widely discussed and recommended, with 216 upvotes and 45 models citing it.\n", |
|
"- Additional resources, including a video review and articles, are available through external links provided by the community.\n", |
|
"\n", |
|
"## Related Research\n", |
|
"The paper is part of a broader trend in enhancing LLMs' reasoning abilities, with related works such as:\n", |
|
"- **Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization (2024)**\n", |
|
"- **Offline Reinforcement Learning for LLM Multi-Step Reasoning (2024)**\n", |
|
"- **Reasoning Language Models: A Blueprint (2025)**\n", |
|
"\n", |
|
"## Availability\n", |
|
"- The paper and models are accessible on [GitHub](https://github.com/deepseek-ai/DeepSeek-R1) and the [arXiv page](https://arxiv.org/abs/2501.12948).\n", |
|
"```" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"import os\n", |
|
"import requests\n", |
|
"from dotenv import load_dotenv\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display, clear_output\n", |
|
"from openai import OpenAI\n", |
|
"import time\n", |
|
"\n", |
|
"load_dotenv(override=True)\n", |
|
"api_key = os.getenv('DEEPSEEK_API_KEY')\n", |
|
"base_url=os.getenv('DEEPSEEK_BASE_URL')\n", |
|
"start_time = time.time()\n", |
|
"\n", |
|
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n", |
|
"and provides a short summary, ignoring text that might be navigation related. \\\n", |
|
"Respond in markdown.\"\n", |
|
"\n", |
|
"messages = [\n", |
|
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", |
|
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", |
|
"]\n", |
|
" \n", |
|
"# Check the key\n", |
|
"if not api_key:\n", |
|
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n", |
|
"elif not api_key.startswith(\"sk-proj-\"):\n", |
|
" print(\"An API key was found, but it doesn't start sk-proj-; Looks like you are using DeepSeek (R1) model.\")\n", |
|
"elif api_key.strip() != api_key:\n", |
|
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n", |
|
"else:\n", |
|
" print(\"API key found and looks good so far!\")\n", |
|
" \n", |
|
"openai = OpenAI(api_key=api_key, base_url=base_url)\n", |
|
"\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", |
|
" def __init__(self, url):\n", |
|
" \"\"\"\n", |
|
" Create this Website object from the given url using the BeautifulSoup library\n", |
|
" \"\"\"\n", |
|
" self.url = url\n", |
|
" response = requests.get(url, headers=headers)\n", |
|
" soup = BeautifulSoup(response.content, 'html.parser')\n", |
|
" self.title = soup.title.string if soup.title else \"No title found\"\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", |
|
" \n", |
|
"def user_prompt_for(website):\n", |
|
" user_prompt = f\"You are looking at a website titled {website.title}\"\n", |
|
" user_prompt += \"\\nThe contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\\n\\n\"\n", |
|
" user_prompt += website.text\n", |
|
" return user_prompt\n", |
|
"\n", |
|
"def messages_for(website):\n", |
|
" return [\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
|
" ]\n", |
|
" \n", |
|
"def summarize(url):\n", |
|
" website = Website(url)\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model=\"deepseek-chat\",\n", |
|
" messages=messages_for(website),\n", |
|
" stream=True\n", |
|
" )\n", |
|
" print(\"Streaming response:\")\n", |
|
" accumulated_content = \"\" # Accumulate the content here\n", |
|
" for chunk in response:\n", |
|
" if chunk.choices[0].delta.content: # Check if there's content in the chunk\n", |
|
" accumulated_content += chunk.choices[0].delta.content # Append the chunk to the accumulated content\n", |
|
" clear_output(wait=True) # Clear the previous output\n", |
|
" display(Markdown(accumulated_content)) # Display the updated content\n", |
|
" \n", |
|
" # # Final display (optional, as the loop already displays the content)\n", |
|
" # display(Markdown(accumulated_content))\n", |
|
"\n", |
|
"def display_summary():\n", |
|
" url = str(input(\"Enter the URL of the website you want to summarize: \"))\n", |
|
" summarize(url)\n", |
|
"\n", |
|
"display_summary()" |
|
] |
|
} |
|
], |
|
"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 |
|
}
|
|
|