Open-weight model
visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean
by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean
Parameters—
Context—
Weights29.0 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- Miiche/visualrl-qwen3vl4b-ppo1-ral-c10-r2-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
- 8c68bdd6bff3e9c7d08bdeecab60457630ad249a
- First published
- 2026-09-17
- Last updated
- 2026-09-18
Files and Weights
191 files, 30.0 GB in total. The weights are 6 files totalling 29.0 GB in safetensors.
Weights6 files · 29.0 GB
Configuration117 files · 231.8 MB
Tokenizer12 files · 47.6 MB
Other55 files · 757.8 MB
Repository1 file · 2.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_180_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | c2b1110bfaa0 |
| global_step_180_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | a0af24bfe23d |
| global_step_270_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | 48e9b52ada17 |
| global_step_270_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | 8ee772a9ee2c |
| global_step_90_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | 2d5216ef921f |
| global_step_90_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | 2b8823aab5a3 |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/blink_output.json | Configuration | 4.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/chartqa_output.json | Configuration | 2.1 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/hallusionbench_output.json | Configuration | 1.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/hallusionbench_scores.json | Configuration | 492 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/logicvista_output.json | Configuration | 1.7 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/logicvista_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathverse_output.json | Configuration | 10.8 MB | ff10ce679171 |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvision_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvision_scores.json | Configuration | 9.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvista_output.json | Configuration | 2.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmbench_output.json | Configuration | 7.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mme_output.json | Configuration | 2.7 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu_output.json | Configuration | 3.7 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu_pro_output.json | Configuration | 196.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu_pro_scores.json | Configuration | 108 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu_scores.json | Configuration | 2.6 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmstar_output.json | Configuration | 3.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmvet_output.json | Configuration | 197.8 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmvet_scores.json | Configuration | 502 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/perceptionbench_output.json | Configuration | 8.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/perceptionbench_scores.json | Configuration | 1.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/realworldqa_output.json | Configuration | 657.2 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/scienceqa_output.json | Configuration | 2.3 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/visnumbench_output.json | Configuration | 3.7 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/visnumbench_scores.json | Configuration | 948 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/blink_output.json | Configuration | 7.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/chartqa_output.json | Configuration | 2.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/hallusionbench_output.json | Configuration | 1.5 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/hallusionbench_scores.json | Configuration | 491 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/logicvista_output.json | Configuration | 3.4 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/logicvista_scores.json | Configuration | 501 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mathvista_output.json | Configuration | 4.1 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmbench_output.json | Configuration | 8.5 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmbench_scores.json | Configuration | 6.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mme_output.json | Configuration | 2.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmmu_output.json | Configuration | 5.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmstar_output.json | Configuration | 5.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmvet_output.json | Configuration | 199.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmvet_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/perceptionbench_output.json | Configuration | 28.7 MB | dd442cdb65a9 |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/perceptionbench_scores.json | Configuration | 1.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/realworldqa_output.json | Configuration | 942.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/scienceqa_output.json | Configuration | 3.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/scienceqa_scores.json | Configuration | 357 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/visnumbench_output.json | Configuration | 8.1 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/visnumbench_scores.json | Configuration | 951 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/blink_output.json | Configuration | 7.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/chartqa_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/chartqa_scores.json | Configuration | 191 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/hallusionbench_output.json | Configuration | 1.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/hallusionbench_scores.json | Configuration | 491 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/logicvista_output.json | Configuration | 2.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/logicvista_scores.json | Configuration | 500 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathverse_output.json | Configuration | 16.6 MB | 3e51606d7b93 |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvision_output.json | Configuration | 2.9 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvision_scores.json | Configuration | 8.9 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvista_output.json | Configuration | 3.7 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmbench_output.json | Configuration | 9.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmbench_scores.json | Configuration | 6.4 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mme_output.json | Configuration | 4.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu_output.json | Configuration | 5.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu_pro_output.json | Configuration | 196.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu_pro_scores.json | Configuration | 110 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmstar_output.json | Configuration | 4.4 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmvet_output.json | Configuration | 202.4 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmvet_scores.json | Configuration | 526 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/perceptionbench_output.json | Configuration | 18.7 MB | 84a7d05b7e82 |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/perceptionbench_scores.json | Configuration | 1.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/realworldqa_output.json | Configuration | 1.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/scienceqa_output.json | Configuration | 3.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/scienceqa_scores.json | Configuration | 359 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/visnumbench_output.json | Configuration | 7.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-ral-c10-r2-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/model.safetensors.index.json | Configuration | 64.8 KB | — |
| 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/model.safetensors.index.json | Configuration | 64.8 KB | — |
| 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/model.safetensors.index.json | Configuration | 64.8 KB | — |
| 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-q3vl4b_ppo1_ral_c10_r2.log | Other | 746.7 MB | c06adfeafe5e |
| logs/eval-visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm.log | Other | 2.2 MB | — |
| logs/eval-visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm.log | Other | 2.3 MB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/blink.log | Other | 164.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/chartqa.log | Other | 99.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/hallusionbench.log | Other | 53.7 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/logicvista.log | Other | 52.2 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathverse.log | Other | 294.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvision.log | Other | 48.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mathvista.log | Other | 75.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmbench.log | Other | 170.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mme.log | Other | 110.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu.log | Other | 107.7 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmmu_pro.log | Other | 170.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmstar.log | Other | 85.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/mmvet.log | Other | 165.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/perceptionbench.log | Other | 262.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/realworldqa.log | Other | 55.8 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/scienceqa.log | Other | 87.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s180-vllm/visnumbench.log | Other | 157.2 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/blink.log | Other | 158.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/chartqa.log | Other | 103.2 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/hallusionbench.log | Other | 54.7 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/logicvista.log | Other | 38.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mathvista.log | Other | 66.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmbench.log | Other | 180.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mme.log | Other | 116.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmmu.log | Other | 95.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmstar.log | Other | 80.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/mmvet.log | Other | 166.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/perceptionbench.log | Other | 230.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/realworldqa.log | Other | 58.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/scienceqa.log | Other | 96.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s270-vllm/visnumbench.log | Other | 111.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/blink.log | Other | 170.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/chartqa.log | Other | 108.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/hallusionbench.log | Other | 62.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/logicvista.log | Other | 54.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathverse.log | Other | 324.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvision.log | Other | 43.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mathvista.log | Other | 82.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmbench.log | Other | 193.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mme.log | Other | 119.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu.log | Other | 107.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmmu_pro.log | Other | 165.8 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmstar.log | Other | 96.6 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/mmvet.log | Other | 166.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/perceptionbench.log | Other | 270.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/realworldqa.log | Other | 59.6 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/scienceqa.log | Other | 101.8 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-ral-c10-r2-clean-s90-vllm/visnumbench.log | Other | 180.9 KB | — |
| train_logs/train_metrics_q3vl4b_ppo1_ral_c10_r2.jsonl | Other | 542.6 KB | — |
| .gitattributes | Repository | 2.3 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
- 29.0 GB
Download from Zeyuan Yang
Released by Zeyuan Yang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 29.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.