gemma-4-12B-it-fp8
FP8 quantized version of google/gemma-4-12B-it (12B params, unified multimodal model). Produced and maintained by vrfai. This model was...
FP8 quantized version of google/gemma-4-12B-it (12B params, unified multimodal model). Produced and maintained by vrfai. This model was...
Munin Ministral 8B is a Danish-focused text-only language model from the Munin 1.0 family. It is post-trained from...
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks A mid-training «practice phase» that teaches small open-source LLMs...
This repository contains the merged SkillFlow Supervisor model weights. — Code: https://github.com/beita6969/SkillFlow — Dataset: https://huggingface.co/datasets/beita6969/SkillFlow-Dataset — Base model:...
An abliterated (uncensored) version of Google’s Gemma 4 E2B Instruct, converted to LiteRT format (.litertlm) for on-device inference....
MACyber-12B is an adaptive 12B-parameter cybersecurity language model designed to bridge security data silos across heterogeneous, structured data...
There are thousands of fine-tuned LLMs on HuggingFace. Hypnos-Q1 is different in three concrete ways: 1. Real hardware...
Locus is a base model with the RLHF voice surgically removed. Same Gemma-4 underneath. Same capabilities. Same safety....
👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are...
> 2026-05-03 Исправление конфигурации: ropescaling.mscalealldim в config.json был исправлен с 1,0 до 0,0, что соответствует исправлению Mistral выше...