Open-weight model
visualrl-qwen3vl4b-ppo1-ral-c001-r2-fix
by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-ral-c001-r2-fix
Parameters—
Context—
Weights203.1 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-c001-r2-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
- 0ebee0c3789bf59eba830a5b1f0d7e9c613b81e9
- First published
- 2026-09-17
- Last updated
- 2026-09-18
Files and Weights
151 files, 203.2 GB in total. The weights are 93 files totalling 203.1 GB in pt.
Weights93 files · 203.1 GB
Configuration30 files · 23.6 KB
Tokenizer20 files · 79.4 MB
Other7 files · 17.3 MB
Repository1 file · 3.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_170/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 0d1d95c2fba7 |
| global_step_170/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 442d236c8ad5 |
| global_step_170/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 3d4070d91e03 |
| global_step_170/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 772da26d00d1 |
| global_step_170/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 29e74512c446 |
| global_step_170/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | d0b62ec5317b |
| global_step_170/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | b291a33d38fa |
| global_step_170/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | ad0e2297aa0e |
| global_step_170/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | fd9575a54570 |
| global_step_170/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | 32da1c0115cc |
| global_step_170/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 83f00f319089 |
| global_step_170/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | e17bc4e5c18c |
| global_step_170/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 046de0f3c2ed |
| global_step_170/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 8758add49138 |
| global_step_170/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | b02d6f05b3c5 |
| global_step_170/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 6f8bfd658d54 |
| global_step_170/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | 9b8c7196eb6c |
| global_step_170/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 415e508ffaf0 |
| global_step_170/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | bd38fbd11e27 |
| global_step_170/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | f01f20162027 |
| global_step_170/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | 4397a22cb446 |
| global_step_170/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | bc50826680ad |
| global_step_170/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | c578e52af0ed |
| global_step_170/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | 75cfa8974a2c |
| global_step_170/dataloader.pt | Weights | 2.0 KB | b6e4e961632d |
| global_step_180/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 1a5685406dbf |
| global_step_180/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 0a20eccb5701 |
| global_step_180/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 957710dbe510 |
| global_step_180/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 1d4b02518728 |
| global_step_180/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 56f160e4f000 |
| global_step_180/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | c468ac2eefe2 |
| global_step_180/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | ee501e0b6a27 |
| global_step_180/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 85f324502582 |
| global_step_180/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 56678e8d20e1 |
| global_step_180/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | a3a2edfd9868 |
| global_step_180/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 9c5c74674543 |
| global_step_180/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | bf96c9ca4ec5 |
| global_step_180/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | f321d6e18c74 |
| global_step_180/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 0c975e22af7a |
| global_step_180/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | fa0682914d8e |
| global_step_180/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 500ddcbc204c |
| global_step_180/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | 08ab1652cd93 |
| global_step_180/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 82a42e49790f |
| global_step_180/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 3e0d3b61af9b |
| global_step_180/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 4f6179428c84 |
| global_step_180/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | a2e7df117135 |
| global_step_180/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | a7ca9dcab7b1 |
| global_step_180/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | b38abafb5bc9 |
| global_step_180/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | ce73e1eac8ce |
| global_step_180/dataloader.pt | Weights | 2.0 KB | d9b1c299d409 |
| global_step_180_highlight/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 56678e8d20e1 |
| global_step_180_highlight/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | a3a2edfd9868 |
| global_step_180_highlight/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 9c5c74674543 |
| global_step_180_highlight/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | bf96c9ca4ec5 |
| global_step_180_highlight/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | f321d6e18c74 |
| global_step_180_highlight/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 0c975e22af7a |
| global_step_180_highlight/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | fa0682914d8e |
| global_step_180_highlight/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 500ddcbc204c |
| global_step_180_highlight/dataloader.pt | Weights | 2.0 KB | d9b1c299d409 |
| 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 | 05cfcde61c76 |
| global_step_90/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | bef9d81a17d1 |
| global_step_90/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 588a02ea8478 |
| global_step_90/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | dc9c74427e6b |
| global_step_90/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 139835fdc30c |
| global_step_90/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | c64d111a6fbe |
| global_step_90/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | a0587f86edd0 |
| global_step_90/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | e0be494df4a2 |
| global_step_90/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | b4057bf79bfe |
| global_step_90/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | f5bd07475b59 |
| global_step_90/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | a016c8e2e521 |
| global_step_90/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 03e36478f7ed |
| global_step_90/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | 0b70af1e43b3 |
| global_step_90/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | 4d5a5f8790c4 |
| global_step_90/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | ba07ad8c1ee4 |
| global_step_90/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | fc713f96156a |
| global_step_90/dataloader.pt | Weights | 2.0 KB | bd0666d2c41b |
| global_step_90_highlight/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 05cfcde61c76 |
| global_step_90_highlight/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | bef9d81a17d1 |
| global_step_90_highlight/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 588a02ea8478 |
| global_step_90_highlight/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | dc9c74427e6b |
| global_step_90_highlight/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 139835fdc30c |
| global_step_90_highlight/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | c64d111a6fbe |
| global_step_90_highlight/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | a0587f86edd0 |
| global_step_90_highlight/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | e0be494df4a2 |
| global_step_90_highlight/dataloader.pt | Weights | 2.0 KB | bd0666d2c41b |
| global_step_170/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_170/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_170/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_170/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_170/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_170/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_180/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_180/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_180/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_180/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_180/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_180/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| global_step_180_highlight/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_180_highlight/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_180_highlight/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_180_highlight/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_180_highlight/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_180_highlight/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_170/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_180/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_180_highlight/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_ral_c001_r2.log | Other | 16.9 MB | ed2afaa6eadd |
| train_logs/train_metrics_q3vl4b_ppo1_ral_c001_r2.jsonl | Other | 361.6 KB | — |
| .gitattributes | Repository | 3.3 KB | — |
| global_step_170/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_170/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_170/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_170/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_180/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_180/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_180/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_180/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| global_step_180_highlight/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_180_highlight/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_180_highlight/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_180_highlight/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
- 203.1 GB
Download from Zeyuan Yang
Released by Zeyuan Yang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 203.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.