Crystal-31B-RL
hiwaifu-research · Kit
A role-play chat model post-trained from Gemma 4 31B-IT that replies in the user's language, whether Russian, Spanish, English or Portuguese, and stays in it.…
New
AI projects from Hugging Face
Categories and filters
Listings
Smaug Humanizer
abacusai · Kit
Rewrites AI-written text in a human voice while keeping its facts, numbers, names and layout. A 12B model fine-tuned by Abacus.AI from Gemma 4, for writers and…
New
gemma-4-12b-constraintkit
shib79 · Kit
A 12B Gemma fine-tune that turns plain English into a parts-and-mates program for the constraint-kit CAD system, and says so when a request is out of scope, fo…
New
Clinassist Train
Gs2004 · Kit
Holds the training scripts and Gradio app used to tune a Qwen model for the author's Clinassist project with GRPO. Suits machine learning developers who want t…
New
Train the agent slides
sergiopaniego · Kit
A browser slide deck on how AI agents are trained with TRL and OpenEnv, from SFT on agent traces to GRPO and RL in environments. Made for developers learning a…
New