Downloads · 30 days
0
logan7000/mllm-cogrpo-heter-qwen25vl-3b-x-internvl35-2b-open-r1-old-groupB-internvl35-2b-full
mllm-cogrpo-heter-qwen25vl-3b-x-internvl35-2b-open-r1-old-groupB-internvl35-2b-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: old (beta 0, K 8, T 1.0, cap 1024, lr 1e-6, warmup 0.03, 8 prompts/step = EB 64), same as big-tier Qwen-7B column. Co-learning; 961 steps. best/ = best-by-val (MathVista-150) step 500; endpoint/ = checkpoint-9…
Downloads · 30 days
0
Access
Public
Updated Sep 2, 2026
Repo size
9.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors9.4 GB · 100%
From the Hugging Face model README
Recipe: old (beta 0, K 8, T 1.0, cap 1024, lr 1e-6, warmup 0.03, 8 prompts/step = EB 64), same as big-tier Qwen-7B column. Co-learning; 961 steps. best/ = best-by-val (MathVista-150) step 500; endpoint/ = checkpoint-961 (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/openr1_heter_qwen25vl3b_x_internvl35_2b_oldv2_20260901_213002/model_b Trained 2026-09-01/02 on JHU a100.