Open-weight model
visualrl-qwen3vl4b-ppo1-ral-c50-r2-fix
by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-ral-c50-r2-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-ral-c50-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
- 85957ca08c1a4b87704a84d2d68459966ca356e7
- First published
- 2026-09-17
- Last updated
- 2026-09-18
Files and Weights
131 files, 194.2 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 · 10.3 GB
Repository1 file · 3.1 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| global_step_160/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 13db9c675d16 |
| global_step_160/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | ba3f44255501 |
| global_step_160/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 8550c03f4b70 |
| global_step_160/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | d5c842691e3b |
| global_step_160/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 6318988ea7c9 |
| global_step_160/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | ab3b4dad2f1d |
| global_step_160/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 62018e1ac066 |
| global_step_160/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 4efeec55bac0 |
| global_step_160/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | b30a39a1beba |
| global_step_160/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | f723e9da1026 |
| global_step_160/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | d6fdef540f68 |
| global_step_160/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | f6e26bbd7324 |
| global_step_160/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 6d45e9335c38 |
| global_step_160/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | 5279469937f1 |
| global_step_160/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | 486e778a53c9 |
| global_step_160/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 52765b36662d |
| global_step_160/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | ee551145d4af |
| global_step_160/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 0d6afedf65bd |
| global_step_160/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | bad161e51ecb |
| global_step_160/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 295d5f9e2112 |
| global_step_160/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | a9eda7206719 |
| global_step_160/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | 7aaca0710aaa |
| global_step_160/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | 72a7e5887c29 |
| global_step_160/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | cf8c9f35f6e3 |
| global_step_160/dataloader.pt | Weights | 2.0 KB | 204ddc68c1ec |
| 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 | 144d4be902f6 |
| global_step_170/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | 46f92d24db60 |
| global_step_170/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 2613427154c6 |
| global_step_170/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 9f029f6cc103 |
| global_step_170/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 5bce10318d09 |
| global_step_170/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | fd3bf88ba5b3 |
| global_step_170/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | 17aa1cbc55e7 |
| global_step_170/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | baa876a4b31a |
| global_step_170/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | cdfedfde00ea |
| global_step_170/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 7ee72cfdd61b |
| global_step_170/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 286d70e846ff |
| global_step_170/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 02f4990b918f |
| global_step_170/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | f543c76c1193 |
| global_step_170/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | 9b822e9d49ec |
| global_step_170/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | 9d33b0458f82 |
| global_step_170/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | 364031e4838b |
| global_step_170/dataloader.pt | Weights | 2.0 KB | affb3ab09d1b |
| 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 | 8ececd569732 |
| global_step_90/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | bf99577bfc4f |
| global_step_90/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 00160ed7a56a |
| global_step_90/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 2e1bb3e7dbb2 |
| global_step_90/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 6fc6db05acd0 |
| global_step_90/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | a038a2366dff |
| global_step_90/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | fe2aaebd4b01 |
| global_step_90/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 62931ef53472 |
| global_step_90/actor/optim_world_size_8_rank_0.pt | Weights | 4.4 GB | fcb682962101 |
| global_step_90/actor/optim_world_size_8_rank_1.pt | Weights | 4.4 GB | 08dc745ccb6b |
| global_step_90/actor/optim_world_size_8_rank_2.pt | Weights | 4.4 GB | 5681ca9f4f3e |
| global_step_90/actor/optim_world_size_8_rank_3.pt | Weights | 4.4 GB | 00632fcdb625 |
| global_step_90/actor/optim_world_size_8_rank_4.pt | Weights | 4.4 GB | bfafb9ca7ef7 |
| global_step_90/actor/optim_world_size_8_rank_5.pt | Weights | 4.4 GB | b61472a3422b |
| global_step_90/actor/optim_world_size_8_rank_6.pt | Weights | 4.4 GB | ac239ced4933 |
| global_step_90/actor/optim_world_size_8_rank_7.pt | Weights | 4.4 GB | c2e7ac42b5d4 |
| global_step_90/dataloader.pt | Weights | 2.0 KB | e98121c432a9 |
| global_step_90_highlight/actor/model_world_size_8_rank_0.pt | Weights | 2.4 GB | 8ececd569732 |
| global_step_90_highlight/actor/model_world_size_8_rank_1.pt | Weights | 2.4 GB | bf99577bfc4f |
| global_step_90_highlight/actor/model_world_size_8_rank_2.pt | Weights | 2.4 GB | 00160ed7a56a |
| global_step_90_highlight/actor/model_world_size_8_rank_3.pt | Weights | 2.4 GB | 2e1bb3e7dbb2 |
| global_step_90_highlight/actor/model_world_size_8_rank_4.pt | Weights | 2.4 GB | 6fc6db05acd0 |
| global_step_90_highlight/actor/model_world_size_8_rank_5.pt | Weights | 2.4 GB | a038a2366dff |
| global_step_90_highlight/actor/model_world_size_8_rank_6.pt | Weights | 2.4 GB | fe2aaebd4b01 |
| global_step_90_highlight/actor/model_world_size_8_rank_7.pt | Weights | 2.4 GB | 62931ef53472 |
| global_step_90_highlight/dataloader.pt | Weights | 2.0 KB | e98121c432a9 |
| global_step_160/actor/huggingface/added_tokens.json | Configuration | 707 B | — |
| global_step_160/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| global_step_160/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| global_step_160/actor/huggingface/preprocessor_config.json | Configuration | 782 B | — |
| global_step_160/actor/huggingface/special_tokens_map.json | Configuration | 613 B | — |
| global_step_160/actor/huggingface/video_preprocessor_config.json | Configuration | 817 B | — |
| 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_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_160/actor/huggingface/chat_template.jinja | Other | 5.3 KB | — |
| global_step_170/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_c50_r2.log | Other | 10.3 GB | 11db10eebe18 |
| train_logs/train_metrics_q3vl4b_ppo1_ral_c50_r2.jsonl | Other | 341.6 KB | — |
| .gitattributes | Repository | 3.1 KB | — |
| global_step_160/actor/huggingface/merges.txt | Tokenizer | 1.7 MB | — |
| global_step_160/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| global_step_160/actor/huggingface/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| global_step_160/actor/huggingface/vocab.json | Tokenizer | 2.8 MB | — |
| 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_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.