Downloads · 30 days
0
logan7000/mllm-cogrpo-heter-qwen25vl-3b-x-internvl35-2b-mmr1-mmupt-groupA-qwen25vl-3b-full
mllm-cogrpo-heter-qwen25vl-3b-x-internvl35-2b-mmr1-mmupt-groupA-qwen25vl-3b-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.
Recipe: mmupt (beta 0.01, K 10, T 0.7, cap 2048, lr 1e-6, warmup 0, weightdecay 0.01, maxgradnorm 1.0, bnpo, scalerewards group, 12 prompts/step = EB 120), same as big-tier InternVL-8B column. Co-learning (both sides…
Downloads · 30 days
0
Access
Public
Updated Sep 2, 2026
Repo size
15 GB
Likes
0
Public
Click a slice to open those files.
.safetensors15 GB · 100%
From the Hugging Face model README
Recipe: mmupt (beta 0.01, K 10, T 0.7, cap 2048, lr 1e-6, warmup 0, weight_decay 0.01, max_grad_norm 1.0, bnpo, scale_rewards group, 12 prompts/step = EB 120), same as big-tier InternVL-8B column. Co-learning (both sides mmupt); 481 steps. This pairing feeds the InternVL column (group B); the Qwen column uses the old-recipe pairing. best/ = best-by-val (MathVista-150) step 400; endpoint/ = checkpoint-481 (1 epoch); training/ = train.log, trainer_state, best_metric.
Eval protocol for the paper tables: v2 (T=0, 16k, boxed prompt, rule + Qwen2.5-32B judge), endpoint selection. Local source: /weka/scratch/jhu/dssg2026-ext-rghani1/yyang331/mllm-repro-out/mllm-co-grpo-dp/mmr1_heter_qwen25vl3b_x_internvl35_2b_mmuptv2_20260902_075445/model_a Trained 2026-09-01/02 on JHU a100.