In this video, I look at the new open source reasoning models that have come out from a number of different companies and how they compare against the OpenAI alternatives. This helps us see just how far behind open source and open weights models are in comparison to the proprietary models from OpenAI.
For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://twitter.com/Sam_Witteveen
DeepSeek R1 Chat: https://chat.deepseek.com/
DeepSeek Info: https://api-docs.deepseek.com/news/news1120
Qwen QwQ Blog: https://qwenlm.github.io/blog/qwq-32b-preview/
QwQ Preview: https://huggingface.co/spaces/Qwen/QwQ-32B-preview
Marco01: https://huggingface.co/AIDC-AI/Marco-o1
Marco01 paper: https://arxiv.org/pdf/2411.14405
OpenAI Launch info: https://openai.com/index/learning-to-reason-with-llms/
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes
👨💻Github:
https://github.com/samwit/langchain-tutorials (updated)
https://github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro OpenAI o1 December Release
00:23 New Reasoning Models
00:52 Learning to Reason with LLMs Blog
01:58 Standard LLM
02:43 Reasoning LLM
03:36 Let's Verify Step by Step Paper
03:58 Chain-of-Thought Prompting Elicits Reasoning in LLMs Paper
06:26 DeepSeek-R1-Light-Preview
06:36 DeepSeek Benchmarks
09:07 DeepSeek Chat Interface Demo
16:04 Qwen-QwQ
16:42 Qwen-QwQ Benchmarks
17:47 Qwen-QwQ Chat Interface Demo
22:10 Marco-o1
22:15 Marco-o1 Paper