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 5 days ago

Sumi: Open Uniform Diffusion Language Model from Scratch

liked a model 5 days ago

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

reacted to fblgit's post with 👍 7 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

liked a model 5 days ago

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

Text Generation • 6B • Updated 8 days ago • 3.24k • 12

liked a model 14 days ago

merve/rf-detr-mobile-ui

Object Detection • 33.4M • Updated 17 days ago • 48 • 1

liked 10 models about 1 month ago

Efficient-Large-Model/LongLive-2.0-5B

Text-to-Video • Updated May 19 • 22

vrgamedevgirl84/LTX_2.3_Fantasy_Puppet_Style_LoRa

Text-to-Video • Updated Apr 24 • 444 • 2

vrgamedevgirl84/LTX_2.3_Soft_Enhance_Style_LoRa

Text-to-Video • Updated Apr 24 • 3.19k • 34

crogers2287/Intern-S2-Preview-FP8-GGUF

Text Generation • Updated May 16 • 1

OmerHagage/ltx2-ume-pixelart-lora

Text-to-Video • Updated May 12 • 2

Pranavz/MythoMax-L2-13b-heretic

13B • Updated May 7 • 5 • 1

unsloth/Qwen3.6-27B-MTP-GGUF

Image-Text-to-Text • 27B • Updated 27 days ago • 875k • 811

unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Image-Text-to-Text • 36B • Updated May 20 • 903k • 567

Osye/mlp-surgery-restored-top30

3B • Updated May 7 • 4 • 2

Osye/mlp-surgery-restored-specificity-top10

3B • Updated May 7 • 5 • 1

liked 3 models about 2 months ago

SulphurAI/Sulphur-2-base

Text-to-Video • 9B • Updated 9 days ago • 933k • 1.75k

poolside/Laguna-XS.2

Text Generation • 33B • Updated 4 days ago • 232k • 310

Xerv-AI/MAXWELL

Text Generation • 2B • Updated about 1 month ago • 178 • 5

liked 3 models 2 months ago

stamsam/FrankenGemma4

Text Generation • 1B • Updated Apr 20 • 54 • 6

YoAbriel/KodaLite-1.3B

Text Generation • 1B • Updated May 4 • 80 • 3

tencent/HY-Embodied-0.5

Image-Text-to-Text • 4B • Updated Apr 14 • 409 • 909

liked 2 models 3 months ago

netflix/void-model

Video-to-Video • Updated Apr 6 • 946

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated Sep 10, 2025 • 621k • 977