Open-weight model
visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean
by Zeyuan Yang Miiche/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean
visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean is an open-weight model from Zeyuan Yang. Its published files total 15.8 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-visionsr1-4bx-c10-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
- 704ca11ec124c335902a3151054758b5b602cc8f
- First published
- 2026-09-17
- Last updated
- 2026-09-19
Files and Weights
243 files, 15.8 GB in total. The weights are 3 files totalling 14.6 GB in safetensors.
Weights3 files · 14.6 GB
Configuration150 files · 267.0 MB
Tokenizer12 files · 47.6 MB
Other77 files · 860.0 MB
Repository1 file · 2.4 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_180_merged/model.safetensors | Weights | 4.9 GB | dfa7abc0284d |
| global_step_270_merged/model.safetensors | Weights | 4.9 GB | fa0cf184c8dc |
| global_step_90_merged/model.safetensors | Weights | 4.9 GB | 78c52903ce8c |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/blink_output.json | Configuration | 6.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/logicvista_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/logicvista_scores.json | Configuration | 489 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/mmstar_output.json | Configuration | 3.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/realworldqa_output.json | Configuration | 993.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/visnumbench_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/visnumbench_scores.json | Configuration | 952 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/blink_output.json | Configuration | 5.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/chartqa_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/hallusionbench_output.json | Configuration | 1.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/hallusionbench_scores.json | Configuration | 493 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/logicvista_output.json | Configuration | 2.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/logicvista_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathverse_output.json | Configuration | 13.9 MB | 3268a4cdc273 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvision_output.json | Configuration | 2.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvista_output.json | Configuration | 3.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvista_scores.json | Configuration | 7.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmbench_output.json | Configuration | 8.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmbench_scores.json | Configuration | 6.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mme_output.json | Configuration | 2.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu_output.json | Configuration | 3.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu_pro_output.json | Configuration | 196.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu_scores.json | Configuration | 2.6 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmstar_output.json | Configuration | 4.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmvet_output.json | Configuration | 252.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmvet_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/perceptionbench_output.json | Configuration | 12.3 MB | fed5e4e846a7 |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/realworldqa_output.json | Configuration | 460.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/realworldqa_scores.json | Configuration | 94 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/scienceqa_output.json | Configuration | 3.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/scienceqa_scores.json | Configuration | 357 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/visnumbench_output.json | Configuration | 5.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/visnumbench_scores.json | Configuration | 922 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/blink_output.json | Configuration | 5.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/logicvista_output.json | Configuration | 992.6 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/logicvista_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/mmstar_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/realworldqa_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/realworldqa_scores.json | Configuration | 94 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/visnumbench_output.json | Configuration | 2.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/visnumbench_scores.json | Configuration | 955 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/blink_output.json | Configuration | 3.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/chartqa_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/hallusionbench_output.json | Configuration | 1.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/hallusionbench_scores.json | Configuration | 492 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/logicvista_output.json | Configuration | 1.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/logicvista_scores.json | Configuration | 501 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathverse_output.json | Configuration | 10.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvision_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvista_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmbench_output.json | Configuration | 7.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mme_output.json | Configuration | 2.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu_output.json | Configuration | 3.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu_pro_output.json | Configuration | 196.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu_pro_scores.json | Configuration | 108 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu_scores.json | Configuration | 2.6 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmstar_output.json | Configuration | 3.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmvet_output.json | Configuration | 234.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmvet_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/perceptionbench_output.json | Configuration | 6.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/realworldqa_output.json | Configuration | 548.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/scienceqa_output.json | Configuration | 2.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/scienceqa_scores.json | Configuration | 344 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/visnumbench_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/visnumbench_scores.json | Configuration | 952 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/blink_output.json | Configuration | 8.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/logicvista_output.json | Configuration | 2.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/logicvista_scores.json | Configuration | 500 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/mmstar_output.json | Configuration | 4.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/realworldqa_output.json | Configuration | 1.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/visnumbench_output.json | Configuration | 5.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/visnumbench_scores.json | Configuration | 949 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/blink_output.json | Configuration | 6.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/chartqa_output.json | Configuration | 2.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/hallusionbench_output.json | Configuration | 1.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/hallusionbench_scores.json | Configuration | 492 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/logicvista_output.json | Configuration | 3.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/logicvista_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathverse_output.json | Configuration | 17.8 MB | 04a09324ccbe |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvision_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvista_output.json | Configuration | 4.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmbench_output.json | Configuration | 9.9 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mme_output.json | Configuration | 2.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu_output.json | Configuration | 5.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu_pro_output.json | Configuration | 196.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu_scores.json | Configuration | 2.6 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmstar_output.json | Configuration | 4.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmvet_output.json | Configuration | 219.8 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmvet_scores.json | Configuration | 504 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/perceptionbench_output.json | Configuration | 17.3 MB | 9000afa674ca |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/realworldqa_output.json | Configuration | 1.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/scienceqa_output.json | Configuration | 4.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/visnumbench_output.json | Configuration | 8.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/visnumbench_scores.json | Configuration | 950 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_4bx_c10.log | Other | 847.3 MB | 3c4f0700b360 |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm.log | Other | 384.5 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm.log | Other | 1.6 MB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm.log | Other | 371.5 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm.log | Other | 1.6 MB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm.log | Other | 386.2 KB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm.log | Other | 1.6 MB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/blink.log | Other | 145.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/logicvista.log | Other | 36.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/mmstar.log | Other | 65.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/realworldqa.log | Other | 53.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-sr1p-vllm/visnumbench.log | Other | 80.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/blink.log | Other | 145.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/chartqa.log | Other | 90.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/hallusionbench.log | Other | 48.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/logicvista.log | Other | 38.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathverse.log | Other | 216.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvision.log | Other | 33.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mathvista.log | Other | 61.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmbench.log | Other | 151.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mme.log | Other | 95.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu.log | Other | 90.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmmu_pro.log | Other | 127.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmstar.log | Other | 76.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/mmvet.log | Other | 44.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/perceptionbench.log | Other | 185.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/realworldqa.log | Other | 50.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/scienceqa.log | Other | 79.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s180-vllm/visnumbench.log | Other | 96.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/blink.log | Other | 144.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/logicvista.log | Other | 31.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/mmstar.log | Other | 63.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/realworldqa.log | Other | 55.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-sr1p-vllm/visnumbench.log | Other | 74.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/blink.log | Other | 142.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/chartqa.log | Other | 90.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/hallusionbench.log | Other | 45.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/logicvista.log | Other | 37.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathverse.log | Other | 216.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvision.log | Other | 35.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mathvista.log | Other | 64.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmbench.log | Other | 146.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mme.log | Other | 95.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu.log | Other | 90.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmmu_pro.log | Other | 138.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmstar.log | Other | 75.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/mmvet.log | Other | 44.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/perceptionbench.log | Other | 181.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/realworldqa.log | Other | 53.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/scienceqa.log | Other | 78.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s270-vllm/visnumbench.log | Other | 94.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/blink.log | Other | 143.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/logicvista.log | Other | 35.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/mmstar.log | Other | 65.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/realworldqa.log | Other | 53.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-sr1p-vllm/visnumbench.log | Other | 84.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/blink.log | Other | 142.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/chartqa.log | Other | 93.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/hallusionbench.log | Other | 48.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/logicvista.log | Other | 38.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathverse.log | Other | 206.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvision.log | Other | 30.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mathvista.log | Other | 61.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmbench.log | Other | 157.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mme.log | Other | 96.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu.log | Other | 86.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmmu_pro.log | Other | 124.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmstar.log | Other | 74.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/mmvet.log | Other | 45.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/perceptionbench.log | Other | 192.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/realworldqa.log | Other | 56.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/scienceqa.log | Other | 82.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-visionsr1-4bx-c10-clean-s90-vllm/visnumbench.log | Other | 101.0 KB | — |
| train_logs/train_metrics_q3vl2b_ppo1_visionsr1_4bx_c10.jsonl | Other | 622.1 KB | — |
| .gitattributes | Repository | 2.4 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.