Open-weight model
visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean
by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean
visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean is an open-weight model from Zeyuan Yang. Its published files total 41.3 GB.
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-ppo1-4bx-c50-L8-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
- d43194065b91fff0248f4602dbff0ee3b527889a
- First published
- 2026-09-22
- Last updated
- 2026-09-23
Files and Weights
106 files, 41.3 GB in total. The weights are 6 files totalling 29.0 GB in safetensors.
Weights6 files · 29.0 GB
Configuration61 files · 108.9 MB
Tokenizer12 files · 47.6 MB
Other26 files · 12.1 GB
Repository1 file · 2.1 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_180_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | b38059770132 |
| global_step_180_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | 7a17419cb25d |
| global_step_270_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | e8593d013662 |
| global_step_270_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | 95bfe4e454bb |
| global_step_90_merged/model-00001-of-00002.safetensors | Weights | 5.0 GB | 4b9aad1d69a4 |
| global_step_90_merged/model-00002-of-00002.safetensors | Weights | 4.7 GB | fdeda4cda704 |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/chartqa_output.json | Configuration | 2.5 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/mmvet_output.json | Configuration | 284.9 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/mmvet_scores.json | Configuration | 501 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/visnumbench_output.json | Configuration | 4.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/visnumbench_scores.json | Configuration | 950 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/blink_output.json | Configuration | 7.3 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/blink_scores.json | Configuration | 3.2 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/chartqa_output.json | Configuration | 3.3 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/chartqa_scores.json | Configuration | 193 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/hallusionbench_output.json | Configuration | 2.0 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/hallusionbench_scores.json | Configuration | 492 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/logicvista_output.json | Configuration | 3.4 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/logicvista_scores.json | Configuration | 499 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathverse_output.json | Configuration | 19.7 MB | c246ccfdcd4e |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathverse_scores.json | Configuration | 2.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvision_output.json | Configuration | 3.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvision_scores.json | Configuration | 9.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvista_output.json | Configuration | 4.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvista_scores.json | Configuration | 7.5 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmbench_output.json | Configuration | 9.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmbench_scores.json | Configuration | 6.3 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mme_output.json | Configuration | 4.3 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mme_scores.json | Configuration | 2.0 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu_output.json | Configuration | 5.6 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu_pro_output.json | Configuration | 196.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu_pro_scores.json | Configuration | 108 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu_scores.json | Configuration | 2.7 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmstar_output.json | Configuration | 5.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmstar_scores.json | Configuration | 3.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmvet_output.json | Configuration | 205.5 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmvet_scores.json | Configuration | 503 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/perceptionbench_output.json | Configuration | 21.1 MB | 5c0a21a79f06 |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/perceptionbench_scores.json | Configuration | 1.1 KB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/realworldqa_output.json | Configuration | 1.2 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/realworldqa_scores.json | Configuration | 95 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/scienceqa_output.json | Configuration | 3.5 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/scienceqa_scores.json | Configuration | 358 B | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/visnumbench_output.json | Configuration | 7.8 MB | — |
| eval_results/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/visnumbench_scores.json | Configuration | 935 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_4bx_c50_L8.log | Other | 12.1 GB | a71cd277a788 |
| logs/eval-visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm.log | Other | 2.1 MB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/chartqa.log | Other | 95.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/mmvet.log | Other | 167.2 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s180-vllm/visnumbench.log | Other | 135.7 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/blink.log | Other | 159.7 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/chartqa.log | Other | 101.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/hallusionbench.log | Other | 58.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/logicvista.log | Other | 45.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathverse.log | Other | 294.5 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvision.log | Other | 37.6 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mathvista.log | Other | 74.1 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmbench.log | Other | 183.8 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mme.log | Other | 117.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu.log | Other | 99.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmmu_pro.log | Other | 147.9 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmstar.log | Other | 90.4 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/mmvet.log | Other | 167.0 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/perceptionbench.log | Other | 235.3 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/realworldqa.log | Other | 59.2 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/scienceqa.log | Other | 93.8 KB | — |
| logs/visualrl-qwen3vl4b-ppo1-4bx-c50-L8-clean-s90-vllm/visnumbench.log | Other | 157.8 KB | — |
| train_logs/train_metrics_q3vl4b_ppo1_4bx_c50_L8.jsonl | Other | 543.6 KB | — |
| .gitattributes | Repository | 2.1 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.