Open-weight model
visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean
by Zeyuan Yang Miiche/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean
visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean is an open-weight model from Zeyuan Yang. Its published files total 30.1 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-ppo1-4bx-c10-Lall-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
- ec7d8e83f212ddb4ec99969ba6e50c04c3600488
- First published
- 2026-09-21
- Last updated
- 2026-09-22
Files and Weights
155 files, 30.1 GB in total. The weights are 3 files totalling 14.6 GB in safetensors.
Weights3 files · 14.6 GB
Configuration94 files · 302.1 MB
Tokenizer12 files · 47.6 MB
Other45 files · 15.1 GB
Repository1 file · 2.8 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_180_merged/model.safetensors | Weights | 4.9 GB | 8e537a909787 |
| global_step_270_merged/model.safetensors | Weights | 4.9 GB | 4e33d2d7455f |
| global_step_90_merged/model.safetensors | Weights | 4.9 GB | 3eaa72cb3d93 |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/blink_output.json | Configuration | 9.7 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/chartqa_output.json | Configuration | 3.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/hallusionbench_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/hallusionbench_scores.json | Configuration | 477 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/logicvista_output.json | Configuration | 4.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/logicvista_scores.json | Configuration | 489 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathverse_output.json | Configuration | 25.5 MB | a2024241165c |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvision_output.json | Configuration | 4.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvision_scores.json | Configuration | 8.8 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvista_output.json | Configuration | 6.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmbench_output.json | Configuration | 14.1 MB | 9b95e556acb2 |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mme_output.json | Configuration | 5.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu_output.json | Configuration | 6.1 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu_pro_output.json | Configuration | 196.4 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu_scores.json | Configuration | 2.6 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmstar_output.json | Configuration | 7.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmvet_output.json | Configuration | 472.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmvet_scores.json | Configuration | 514 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/perceptionbench_output.json | Configuration | 24.0 MB | b5d4bdc5b15f |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/perceptionbench_scores.json | Configuration | 1.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/realworldqa_output.json | Configuration | 2.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/scienceqa_output.json | Configuration | 6.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/visnumbench_output.json | Configuration | 11.1 MB | 8e70a3a00e1b |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/visnumbench_scores.json | Configuration | 953 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/chartqa_output.json | Configuration | 2.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/chartqa_scores.json | Configuration | 191 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/mmvet_output.json | Configuration | 420.9 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/mmvet_scores.json | Configuration | 490 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/realworldqa_output.json | Configuration | 1.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/visnumbench_output.json | Configuration | 9.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/visnumbench_scores.json | Configuration | 951 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/blink_output.json | Configuration | 10.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/chartqa_output.json | Configuration | 3.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/hallusionbench_output.json | Configuration | 3.8 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/hallusionbench_scores.json | Configuration | 493 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/logicvista_output.json | Configuration | 5.0 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/logicvista_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathverse_output.json | Configuration | 31.2 MB | d49652e7420e |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvision_output.json | Configuration | 4.4 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvision_scores.json | Configuration | 8.8 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvista_output.json | Configuration | 7.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmbench_output.json | Configuration | 15.4 MB | 1c17b0b8a773 |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmbench_scores.json | Configuration | 6.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mme_output.json | Configuration | 5.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu_output.json | Configuration | 7.2 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu_pro_output.json | Configuration | 196.3 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmstar_output.json | Configuration | 8.3 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmvet_output.json | Configuration | 428.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmvet_scores.json | Configuration | 516 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/perceptionbench_output.json | Configuration | 29.8 MB | e87c32a31b76 |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/perceptionbench_scores.json | Configuration | 1.1 KB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/realworldqa_output.json | Configuration | 2.6 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/scienceqa_output.json | Configuration | 7.5 MB | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/visnumbench_output.json | Configuration | 12.7 MB | 5bbeee301c0b |
| eval_results/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/visnumbench_scores.json | Configuration | 953 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_4bx_c10_Lall.log | Other | 15.1 GB | 3f082e75428e |
| logs/eval-visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm.log | Other | 1.6 MB | — |
| logs/eval-visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm.log | Other | 1.6 MB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/blink.log | Other | 145.4 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/chartqa.log | Other | 105.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/hallusionbench.log | Other | 50.5 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/logicvista.log | Other | 31.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathverse.log | Other | 196.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvision.log | Other | 28.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mathvista.log | Other | 61.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmbench.log | Other | 164.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mme.log | Other | 108.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu.log | Other | 84.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmmu_pro.log | Other | 116.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmstar.log | Other | 73.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/mmvet.log | Other | 45.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/perceptionbench.log | Other | 183.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/realworldqa.log | Other | 59.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/scienceqa.log | Other | 86.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s180-vllm/visnumbench.log | Other | 88.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/chartqa.log | Other | 101.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/mmvet.log | Other | 46.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/realworldqa.log | Other | 58.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s270-vllm/visnumbench.log | Other | 90.9 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/blink.log | Other | 146.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/chartqa.log | Other | 108.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/hallusionbench.log | Other | 51.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/logicvista.log | Other | 32.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathverse.log | Other | 197.7 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvision.log | Other | 25.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mathvista.log | Other | 61.6 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmbench.log | Other | 162.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mme.log | Other | 110.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu.log | Other | 81.8 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmmu_pro.log | Other | 113.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmstar.log | Other | 75.0 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/mmvet.log | Other | 46.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/perceptionbench.log | Other | 184.1 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/realworldqa.log | Other | 61.3 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/scienceqa.log | Other | 88.2 KB | — |
| logs/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-clean-s90-vllm/visnumbench.log | Other | 85.2 KB | — |
| train_logs/train_metrics_q3vl2b_ppo1_4bx_c10_Lall.jsonl | Other | 544.0 KB | — |
| .gitattributes | Repository | 2.8 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.