Open-weight model
visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean
by Zeyuan Yang Miiche/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean
visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean is an open-weight model from Zeyuan Yang. Its published files total 23.8 GB.
Parameters—
Context—
Weights14.6 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- Miiche/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean
- Publisher
- Zeyuan Yang
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- b03e0c05fb80ad28f5272c42a51bec5dc33d789b
- First published
- 2026-09-15
- Last updated
- 2026-09-19
Files and Weights
243 files, 23.8 GB in total. The weights are 3 files totalling 14.6 GB in safetensors.
Weights3 files · 14.6 GB
Configuration150 files · 303.0 MB
Tokenizer12 files · 47.6 MB
Other77 files · 8.8 GB
Repository1 file · 2.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_180_merged/model.safetensors | Weights | 4.9 GB | bdef369de0ca |
| global_step_270_merged/model.safetensors | Weights | 4.9 GB | 318cdf183ad5 |
| global_step_90_merged/model.safetensors | Weights | 4.9 GB | a3d493c4b71b |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/blink_output.json | Configuration | 9.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/logicvista_output.json | Configuration | 1.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/logicvista_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/mmstar_output.json | Configuration | 4.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/realworldqa_output.json | Configuration | 1.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/visnumbench_output.json | Configuration | 4.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/visnumbench_scores.json | Configuration | 948 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/blink_output.json | Configuration | 5.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/chartqa_output.json | Configuration | 2.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/hallusionbench_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/hallusionbench_scores.json | Configuration | 492 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/logicvista_output.json | Configuration | 2.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/logicvista_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathverse_output.json | Configuration | 13.9 MB | 3adcb3d9429d |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvision_output.json | Configuration | 2.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvista_output.json | Configuration | 3.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmbench_output.json | Configuration | 8.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmbench_scores.json | Configuration | 6.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mme_output.json | Configuration | 2.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu_output.json | Configuration | 4.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu_pro_output.json | Configuration | 196.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu_pro_scores.json | Configuration | 108 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmstar_output.json | Configuration | 3.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmvet_output.json | Configuration | 252.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmvet_scores.json | Configuration | 489 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/perceptionbench_output.json | Configuration | 13.3 MB | b01f31011b63 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/realworldqa_output.json | Configuration | 827.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/scienceqa_output.json | Configuration | 3.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/visnumbench_output.json | Configuration | 5.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/visnumbench_scores.json | Configuration | 954 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/blink_output.json | Configuration | 8.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/logicvista_output.json | Configuration | 1.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/logicvista_scores.json | Configuration | 501 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/mmstar_output.json | Configuration | 4.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/realworldqa_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/visnumbench_output.json | Configuration | 4.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/visnumbench_scores.json | Configuration | 951 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/blink_output.json | Configuration | 4.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/chartqa_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/hallusionbench_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/hallusionbench_scores.json | Configuration | 493 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/logicvista_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/logicvista_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathverse_output.json | Configuration | 12.9 MB | 771bb18a9c00 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvision_output.json | Configuration | 2.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvision_scores.json | Configuration | 9.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvista_output.json | Configuration | 3.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmbench_output.json | Configuration | 8.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mme_output.json | Configuration | 2.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu_output.json | Configuration | 3.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu_pro_output.json | Configuration | 196.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmstar_output.json | Configuration | 3.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmvet_output.json | Configuration | 258.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmvet_scores.json | Configuration | 516 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/perceptionbench_output.json | Configuration | 10.8 MB | ae2e1f37251e |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/realworldqa_output.json | Configuration | 833.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/scienceqa_output.json | Configuration | 3.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/scienceqa_scores.json | Configuration | 357 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/visnumbench_output.json | Configuration | 4.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/visnumbench_scores.json | Configuration | 952 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/blink_output.json | Configuration | 10.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/logicvista_output.json | Configuration | 2.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/logicvista_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/mmstar_output.json | Configuration | 5.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/realworldqa_output.json | Configuration | 1.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/visnumbench_output.json | Configuration | 5.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/visnumbench_scores.json | Configuration | 939 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/blink_output.json | Configuration | 6.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/chartqa_output.json | Configuration | 2.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/hallusionbench_output.json | Configuration | 1.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/hallusionbench_scores.json | Configuration | 493 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/logicvista_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/logicvista_scores.json | Configuration | 500 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathverse_output.json | Configuration | 19.6 MB | ffd20c9e5a29 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvision_output.json | Configuration | 3.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvista_output.json | Configuration | 4.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmbench_output.json | Configuration | 10.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mme_output.json | Configuration | 2.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu_output.json | Configuration | 5.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu_pro_output.json | Configuration | 196.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu_scores.json | Configuration | 2.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmstar_output.json | Configuration | 4.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmvet_output.json | Configuration | 256.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmvet_scores.json | Configuration | 500 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/perceptionbench_output.json | Configuration | 16.4 MB | 8c7ddb2ea541 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/realworldqa_output.json | Configuration | 926.8 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/scienceqa_output.json | Configuration | 4.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/visnumbench_output.json | Configuration | 8.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/visnumbench_scores.json | Configuration | 954 B | — |
| global_step_180_merged/added_tokens.json | Configuration | 707 B | — |
| global_step_180_merged/config.json | Configuration | 1.6 KB | — |
| global_step_180_merged/generation_config.json | Configuration | 147 B | — |
| global_step_180_merged/preprocessor_config.json | Configuration | 782 B | — |
| global_step_180_merged/special_tokens_map.json | Configuration | 613 B | — |
| global_step_180_merged/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_270_merged/added_tokens.json | Configuration | 707 B | — |
| global_step_270_merged/config.json | Configuration | 1.6 KB | — |
| global_step_270_merged/generation_config.json | Configuration | 147 B | — |
| global_step_270_merged/preprocessor_config.json | Configuration | 782 B | — |
| global_step_270_merged/special_tokens_map.json | Configuration | 613 B | — |
| global_step_270_merged/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_90_merged/added_tokens.json | Configuration | 707 B | — |
| global_step_90_merged/config.json | Configuration | 1.6 KB | — |
| global_step_90_merged/generation_config.json | Configuration | 147 B | — |
| global_step_90_merged/preprocessor_config.json | Configuration | 782 B | — |
| global_step_90_merged/special_tokens_map.json | Configuration | 613 B | — |
| global_step_90_merged/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_180_merged/chat_template.jinja | Other | 5.3 KB | — |
| global_step_270_merged/chat_template.jinja | Other | 5.3 KB | — |
| global_step_90_merged/chat_template.jinja | Other | 5.3 KB | — |
| logs/eval-train-q3vl2b_ppo1_visionsr1_r91.log | Other | 8.8 GB | f9397d8c867e |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm.log | Other | 399.7 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm.log | Other | 1.7 MB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm.log | Other | 400.8 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm.log | Other | 1.7 MB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm.log | Other | 402.7 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm.log | Other | 1.7 MB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/blink.log | Other | 150.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/logicvista.log | Other | 37.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/mmstar.log | Other | 69.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/realworldqa.log | Other | 55.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-sr1p-vllm/visnumbench.log | Other | 84.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/blink.log | Other | 144.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/chartqa.log | Other | 99.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/hallusionbench.log | Other | 49.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/logicvista.log | Other | 40.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathverse.log | Other | 223.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvision.log | Other | 33.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mathvista.log | Other | 67.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmbench.log | Other | 157.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mme.log | Other | 100.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu.log | Other | 92.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmmu_pro.log | Other | 139.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmstar.log | Other | 78.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/mmvet.log | Other | 45.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/perceptionbench.log | Other | 199.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/realworldqa.log | Other | 54.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/scienceqa.log | Other | 82.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s180-vllm/visnumbench.log | Other | 109.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/blink.log | Other | 149.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/logicvista.log | Other | 37.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/mmstar.log | Other | 68.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/realworldqa.log | Other | 55.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-sr1p-vllm/visnumbench.log | Other | 87.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/blink.log | Other | 144.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/chartqa.log | Other | 89.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/hallusionbench.log | Other | 48.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/logicvista.log | Other | 40.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathverse.log | Other | 228.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvision.log | Other | 35.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mathvista.log | Other | 65.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmbench.log | Other | 153.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mme.log | Other | 97.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu.log | Other | 92.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmmu_pro.log | Other | 140.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmstar.log | Other | 79.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/mmvet.log | Other | 44.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/perceptionbench.log | Other | 191.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/realworldqa.log | Other | 53.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/scienceqa.log | Other | 80.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s270-vllm/visnumbench.log | Other | 107.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/blink.log | Other | 153.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/logicvista.log | Other | 35.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/mmstar.log | Other | 69.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/realworldqa.log | Other | 55.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-sr1p-vllm/visnumbench.log | Other | 86.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/blink.log | Other | 144.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/chartqa.log | Other | 101.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/hallusionbench.log | Other | 50.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/logicvista.log | Other | 37.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathverse.log | Other | 214.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvision.log | Other | 30.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mathvista.log | Other | 64.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmbench.log | Other | 170.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mme.log | Other | 101.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu.log | Other | 90.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmmu_pro.log | Other | 128.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmstar.log | Other | 78.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/mmvet.log | Other | 45.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/perceptionbench.log | Other | 194.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/realworldqa.log | Other | 58.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/scienceqa.log | Other | 86.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-r91-clean-s90-vllm/visnumbench.log | Other | 104.4 KB | — |
| train_logs/train_metrics_q3vl2b_ppo1_visionsr1_r91.jsonl | Other | 247.4 KB | — |
| .gitattributes | Repository | 2.6 KB | — |
| global_step_180_merged/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_180_merged/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_180_merged/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_180_merged/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_270_merged/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_270_merged/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_270_merged/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_270_merged/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_90_merged/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_90_merged/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_90_merged/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_90_merged/vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 14.6 GB
Download from Zeyuan Yang
Released by Zeyuan Yang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.