Hugging Face's logo
Mike Ravkine's picture
Open to Collab
49 22 626

Mike Ravkine PRO

mike-ravkine
kramp's profile picture Regibillions8's profile picture John6666's profile picture
·

AI & ML interests

LLM Research / Development / Evaluation

Recent Activity

posted an update about 1 hour ago
In case you missed it, I had some fun playing with https://huggingface.co/allura-forge/Llama-3.3-8B-Instruct over the holidays - its not every day that we get a new "old llama". https://huggingface.co/blog/mike-ravkine/new-old-llamas
liked a model 4 days ago
0xSero/DeepSeek-V3.2-REAP-345B-W3A16
posted an update 7 days ago
My hat is off to the https://huggingface.co/upstage team 🎩 https://huggingface.co/upstage/Solar-Open-100B is a very interesting, permissively licensed (Apache-with-attribution), trained from scratch (19T tokens), 12B active MoE - but that's not even the cool part. The cool part is that their fork of vLLM comes with the addition of a `reasoning_effort` parameter and a corresponding reasoning/tool-calling controller FSM to consume it! https://github.com/UpstageAI/vllm/blob/c9a05e077cd82df8cab4f729396c178c29c81aa8/vllm/model_executor/models/solar_open_logits_processor.py Looks like only "medium" and "high" are actually implemented, but still absolutely love to see this sorta thing. To make this model a little more accessible, I have created a FP8-Dynamic quant at https://huggingface.co/mike-ravkine/Solar-Open-100B-FP8-Dynamic which makes it fit nicely into 2xPro-6000 or 4xA6000 GPUs. My ReasonScape evaluations are currently running, will take me a couple days for this one but early results are quite strong: it's showing the competency expected from a 100B reasoning model (it can count the r's in strawberry, it can do basic arithmetic, etc..) and I haven't seen a truncation yet.
View all activity

Organizations

None yet