sharih

74 karma · joined December 14, 2024

sharih··on Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

most of these dev clones need fine tuning on your use case, might as well fine tune modernBERT then. Jev generalizes well while being fast and cheap

sharih··on Jeeves. Reasoning improves Jev-like decision models

What is the point of this, if it is p90 17 seconds? Might as well use an LLM. The beauty of Jev is that it is dirt cheap and insanely fast.

sharih··on Llama.cpp Now Supports Qwen2-VL (Vision Language Model)

Groq limits context window to 8192 is that your experience too

sharih··on Llama.cpp Now Supports Qwen2-VL (Vision Language Model)

Agree. It is amazing that you can run an o1 style model on a Mac. I was able to run QwQ on my 24GB M3 MacBook Air, though results on complex reasoning on domain specific tasks did not work well, and I saw the Chinese 'thinking' too (they don't work well in o1 either). It opens up experimentation which is great, and the reasoning traces for domain specific tasks for RL is where the next improvements are going to come from

sharih··on Sharing new research, models, and datasets from Meta FAIR

This is a great video - places o1 in context. with openAI, google and meta releases going at it at this pace, anthropic is next up..

sharih··on Ilya Sutskever NeurIPS talk [video]

legal reasoning involves applying facts to the law, and it needs knowledge of the world. the expertise of a professional is in picking the right/winning path based on their study of the law, the facts and their real world training. money is in codifying that to teach models to do the same

sharih··on Ilya Sutskever NeurIPS talk [video]

the big frontier models already have all laws, regulations and cases memorized/trained on given they are public. the real advancement is in experts codifying their expertise/reasoning for models to learn from. legal is no different from other fields in this.