Skip to content

logan7000

mllm-mmr1-ttrl-gemma3-4b-full-end-s722

logan7000/mllm-mmr1-ttrl-gemma3-4b-full-end-s722

mllm-mmr1-ttrl-gemma3-4b-full-end-s722 is a reinforcement learning model from logan7000. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.

Fine-tuned from google/gemma-3-4b-it with TTRL / un-GRPO-maj: no labels, trained against the model's own self-consistency majority over its rollouts.

Downloads · 30 days

8

11% of all-time downloads

All-time downloads

70

Public

Parameters

769K

8.6 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors8.6 GB · 100%

At a glance

Task
Reinforcement Learning
License
gemma
Model type
gemma3
Access
Public
Created
Aug 8, 2026
Updated
Aug 8, 2026
SHA
2bbbcec2

Base models

Task
Reinforcement Learning
Type
gemma3
License
gemma
Created
Aug 8, 2026
Updated
Aug 8, 2026