Open-weight model
visualrl-qwen3vl4b-ppo1-dapo-4bx-c10-fix
by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-dapo-4bx-c10-fix
Parameters—
Context—
Weights183.8 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-dapo-4bx-c10-fix
- 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
- 8a3e09ff2de46de15887574041bee36ada36d855
- First published
- 2026-09-15
- Last updated
- 2026-09-18
Files and Weights
131 files, 183.8 GB in total. The weights are 84 files totalling 183.8 GB in pt.
Weights84 files · 183.8 GB
Configuration24 files · 18.9 KB
Tokenizer16 files · 63.5 MB
Other6 files · 3.1 MB
Repository1 file · 2.9 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_130/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | cf1ead5140e3 |
| global_step_130/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 994323dc0bc6 |
| global_step_130/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | ae5931f127a1 |
| global_step_130/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 507ccac45f1c |
| global_step_130/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 7479596455b7 |
| global_step_130/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | d36e9675c633 |
| global_step_130/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 2cab9c3c11c0 |
| global_step_130/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | ab59210294d0 |
| global_step_130/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 2a99b42dd337 |
| global_step_130/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | 1b9737dcc59c |
| global_step_130/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 830f3dccb633 |
| global_step_130/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 873074082826 |
| global_step_130/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 010b31c01a91 |
| global_step_130/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 417160e2102f |
| global_step_130/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | c2f9770806e1 |
| global_step_130/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 80b1e9f96ad1 |
| global_step_130/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | d290a5ff6f21 |
| global_step_130/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 4028f852e71d |
| global_step_130/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 6abaec06f49a |
| global_step_130/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 57e1b0e427dc |
| global_step_130/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | a35ef8a14f59 |
| global_step_130/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | ecc951ee3524 |
| global_step_130/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | c9c35e55eb12 |
| global_step_130/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | 252dfe978c79 |
| global_step_130/dataloader.pt | Weights | 2.0 KB | 07f27bb1cfad |
| global_step_140/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | d13b1eca04a4 |
| global_step_140/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 77084d19d17f |
| global_step_140/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | f8c5b764763a |
| global_step_140/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | f10bf95654b6 |
| global_step_140/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 4f7e0c21e301 |
| global_step_140/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | e618274ae7ed |
| global_step_140/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 436defd70e9f |
| global_step_140/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 48f5985775d4 |
| global_step_140/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | ef2bd2653501 |
| global_step_140/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | b2557f87842d |
| global_step_140/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 82cf1059f9ea |
| global_step_140/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | e890cde01bca |
| global_step_140/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 867b8f2a0452 |
| global_step_140/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 4859e9819e9c |
| global_step_140/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | f5ae32655793 |
| global_step_140/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 26619fc71dae |
| global_step_140/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | f228cf96b4ef |
| global_step_140/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 33a4ccaa997a |
| global_step_140/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 964a0ff1b49b |
| global_step_140/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | c9db82ecfd2f |
| global_step_140/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | 9ee85b831313 |
| global_step_140/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | 6fe951bb797c |
| global_step_140/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | 59df2358760b |
| global_step_140/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | bf72f48277b8 |
| global_step_140/dataloader.pt | Weights | 2.0 KB | e2180501bb09 |
| global_step_90/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 760f13a304a9 |
| global_step_90/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 83acfe9c6fac |
| global_step_90/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 181d82b502f4 |
| global_step_90/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 1a9e29da286b |
| global_step_90/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | d0724d72ee50 |
| global_step_90/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | b7e69923a7e6 |
| global_step_90/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 039cb36a9643 |
| global_step_90/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 968346d925d6 |
| global_step_90/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 546c75c20af1 |
| global_step_90/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | 5608d1d9ce8b |
| global_step_90/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | bfcc995e02ce |
| global_step_90/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 47ea9c34f3a6 |
| global_step_90/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 755d2e80ecb5 |
| global_step_90/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 161178f61b49 |
| global_step_90/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | e494c10ec31f |
| global_step_90/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | e6f05e6b0a08 |
| global_step_90/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | 03944b883651 |
| global_step_90/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | dcea3cbb7d64 |
| global_step_90/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 6730e70be5ad |
| global_step_90/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 887e4cb49e87 |
| global_step_90/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | b23d9ba525a1 |
| global_step_90/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | a453ba045b68 |
| global_step_90/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | c205ec711d2d |
| global_step_90/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | 820a885c3c7f |
| global_step_90/dataloader.pt | Weights | 2.0 KB | 326118f9a2d1 |
| global_step_90_highlight/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 546c75c20af1 |
| global_step_90_highlight/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | 5608d1d9ce8b |
| global_step_90_highlight/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | bfcc995e02ce |
| global_step_90_highlight/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 47ea9c34f3a6 |
| global_step_90_highlight/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 755d2e80ecb5 |
| global_step_90_highlight/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 161178f61b49 |
| global_step_90_highlight/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | e494c10ec31f |
| global_step_90_highlight/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | e6f05e6b0a08 |
| global_step_90_highlight/dataloader.pt | Weights | 2.0 KB | 326118f9a2d1 |
| global_step_130/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_130/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_130/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_130/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_130/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_130/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_140/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_140/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_140/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_140/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_140/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_140/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_90/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_90/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_90/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_90/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_90/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_90/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_90_highlight/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_90_highlight/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_90_highlight/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_90_highlight/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_90_highlight/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_90_highlight/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_130/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_140/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_90/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_90_highlight/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| logs/eval-train-q3vl4b_ppo1_dapo_4bx_c10.log | Other | 2.8 MB | 65751578bbab |
| train_logs/train_metrics_q3vl4b_ppo1_dapo_4bx_c10.jsonl | Other | 256.1 KB | — |
| .gitattributes | Repository | 2.9 KB | — |
| global_step_130/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_130/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_130/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_130/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_140/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_140/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_140/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_140/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_90/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_90/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_90/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_90/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_90_highlight/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_90_highlight/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_90_highlight/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_90_highlight/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 183.8 GB
Download from Zeyuan Yang
Released by Zeyuan Yang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 183.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.