I ran some local tests with deepseek-r1 (a distilled version using Llama and Qwen). The reasoning output is impressive and can even be used to enhance smaller LLMs.
Now there is a new release of qwen which includes an improved HTML document “parsing” part and many other features.
https://qwenlm.github.io/blog/qwen2.5-vl/
https://ollama.com/library/deepseek-r1
[#]llm #ai #opensource
=> More informations about this toot | View the thread | More toots from a@paperbay.org
=> View llm tag | View ai tag | View opensource tag This content has been proxied by September (3851b).Proxy Information
text/gemini