Downloads · 30 days
0
logan7000/mllm-mmr1-gt-qwen25vl7b-mmupt-full
mllm-mmr1-gt-qwen25vl7b-mmupt-full is a machine learning model from logan7000. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
GRPO with ground-truth rewards, MMR1-Math-RL-Data-v0, 481 steps (mmupt recipe: beta=0.01, 10 generations/prompt), for the big-tier GT row.
Downloads · 30 days
0
Access
Public
Updated Sep 1, 2026
Repo size
232 GB
Likes
0
Public
Click a slice to open those files.
.pt199 GB · 86%
From the Hugging Face model README
GRPO with ground-truth rewards, MMR1-Math-RL-Data-v0, 481 steps (mmupt recipe: beta=0.01, 10 generations/prompt), for the big-tier GT row.
| folder | step | note |
|---|---|---|
best/ | 140 | best in-loop val (eval_reward = 0.5724) |
endpoint/ | 481 | end of training |
training/ holds best_metric.json, both trainer_state files, train.log,
and the Slurm joblog.
Distinguishes from the older same-name cell by step count: this run is 481 steps (mmupt), the earlier GT is 722 steps.