s3nh's picture

Open to Collab

s3nh PRO

s3nh

·

s3nhxx
s3nh

AI & ML interests

Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh

Recent Activity

upvoted a paper 2 days ago

Sumi: Open Uniform Diffusion Language Model from Scratch

liked a model 3 days ago

DJLougen/Qwen3.6-35B-A3B-REAP-90pct-GGUF

reacted to fblgit's post with 👍 4 days ago

Introducing `HarEmb - PII` a single-transformer-block distilled layer from OpenMed PII Privacy filter. Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model. It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint. The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model. https://huggingface.co/fblgit/haremb-privacy-filter-opennemo I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model. Contact xavi@juanako.ai

View all activity

Organizations

s3nh 's datasets 1

s3nh/alpaca-dolly-instruction-only-polish

Viewer • Updated May 2, 2023 • 23.7k • 23 • 6