Skip to page content
SAVRN
Search Plan a project

Open-weight model

visualrl-qwen3vl4b-ppo1-4cx-c50-fix

by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-4cx-c50-fix

visualrl-qwen3vl4b-ppo1-4cx-c50-fix is an open-weight model from Zeyuan Yang. Its published files total 200.2 GB.

Parameters—
Context—
Weights183.7 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-ppo1-4cx-c50-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
e27b213ad774ed60d60b94e7766f9b9d2c3c3851
First published
2026-09-23
Last updated
2026-09-24

Files and Weights

91 files, 200.2 GB in total. The weights are 44 files totalling 183.7 GB in pt.

Weights44 files · 183.7 GB
Configuration24 files · 18.9 KB
Tokenizer16 files · 63.5 MB
Other6 files · 16.4 GB
Repository1 file · 3.1 KB
Every file
FileTypeSizeSHA-256
global_step_160/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 21dafce6c7fd
global_step_160/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB caa5b7c8e8b3
global_step_160/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 1592f83c3749
global_step_160/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB c10dcaeff518
global_step_160/actor/model_world_size_4_rank_0.ptWeights4.8 GB 8777f847d331
global_step_160/actor/model_world_size_4_rank_1.ptWeights4.8 GB a38e88f4b2d1
global_step_160/actor/model_world_size_4_rank_2.ptWeights4.8 GB 749c2ed04f1c
global_step_160/actor/model_world_size_4_rank_3.ptWeights4.8 GB ec44190bd259
global_step_160/actor/optim_world_size_4_rank_0.ptWeights8.9 GB 7d710f9282bf
global_step_160/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 2dd82cb5dd0e
global_step_160/actor/optim_world_size_4_rank_2.ptWeights8.9 GB ef1bac6cc3ce
global_step_160/actor/optim_world_size_4_rank_3.ptWeights8.9 GB f7ff1783e67f
global_step_160/dataloader.ptWeights2.0 KB 1cb74de0b87b
global_step_170/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 505d5c6f4f96
global_step_170/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB c734f8dcdebd
global_step_170/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 68231ed184d6
global_step_170/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 366d9ee5c735
global_step_170/actor/model_world_size_4_rank_0.ptWeights4.8 GB 462c0350a9c8
global_step_170/actor/model_world_size_4_rank_1.ptWeights4.8 GB 7d97b71141a5
global_step_170/actor/model_world_size_4_rank_2.ptWeights4.8 GB 8287b7b09ea1
global_step_170/actor/model_world_size_4_rank_3.ptWeights4.8 GB 683500da86b7
global_step_170/actor/optim_world_size_4_rank_0.ptWeights8.9 GB 697ece3deafd
global_step_170/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 32b9136952c1
global_step_170/actor/optim_world_size_4_rank_2.ptWeights8.9 GB a04801f6a1d0
global_step_170/actor/optim_world_size_4_rank_3.ptWeights8.9 GB 1c7cbff70475
global_step_170/dataloader.ptWeights2.0 KB 13b3081fe8d4
global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 51d9abb1fd31
global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 31da6f58d250
global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB b1a67b6aaf81
global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB ed84249b2b36
global_step_90/actor/model_world_size_4_rank_0.ptWeights4.8 GB 1288fb494e83
global_step_90/actor/model_world_size_4_rank_1.ptWeights4.8 GB e8d583659426
global_step_90/actor/model_world_size_4_rank_2.ptWeights4.8 GB 78611661f921
global_step_90/actor/model_world_size_4_rank_3.ptWeights4.8 GB 6ac48ed97d19
global_step_90/actor/optim_world_size_4_rank_0.ptWeights8.9 GB e1df8dd4385a
global_step_90/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 604829303007
global_step_90/actor/optim_world_size_4_rank_2.ptWeights8.9 GB cece17742d06
global_step_90/actor/optim_world_size_4_rank_3.ptWeights8.9 GB 428b33533d4f
global_step_90/dataloader.ptWeights2.0 KB 16580dc22368
global_step_90_highlight/actor/model_world_size_4_rank_0.ptWeights4.8 GB 1288fb494e83
global_step_90_highlight/actor/model_world_size_4_rank_1.ptWeights4.8 GB e8d583659426
global_step_90_highlight/actor/model_world_size_4_rank_2.ptWeights4.8 GB 78611661f921
global_step_90_highlight/actor/model_world_size_4_rank_3.ptWeights4.8 GB 6ac48ed97d19
global_step_90_highlight/dataloader.ptWeights2.0 KB 16580dc22368
global_step_160/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_160/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_160/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_160/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_160/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_160/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
global_step_170/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_170/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_170/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_170/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_170/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_170/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
global_step_90/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_90/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_90/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_90/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_90/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
global_step_90_highlight/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_90_highlight/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_90_highlight/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_90_highlight/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_90_highlight/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_90_highlight/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
global_step_160/actor/huggingface/chat_template.jinjaOther5.3 KB —
global_step_170/actor/huggingface/chat_template.jinjaOther5.3 KB —
global_step_90/actor/huggingface/chat_template.jinjaOther5.3 KB —
global_step_90_highlight/actor/huggingface/chat_template.jinjaOther5.3 KB —
logs/eval-train-q3vl4b_ppo1_4cx_c50.logOther16.4 GB 421edb7121b8
train_logs/train_metrics_q3vl4b_ppo1_4cx_c50.jsonlOther342.6 KB —
.gitattributesRepository3.1 KB —
global_step_160/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_160/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_160/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_160/actor/huggingface/vocab.jsonTokenizer2.8 MB —
global_step_170/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_170/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_170/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_170/actor/huggingface/vocab.jsonTokenizer2.8 MB —
global_step_90/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_90/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_90/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_90/actor/huggingface/vocab.jsonTokenizer2.8 MB —
global_step_90_highlight/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_90_highlight/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_90_highlight/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_90_highlight/actor/huggingface/vocab.jsonTokenizer2.8 MB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
183.7 GB
Download from Zeyuan Yang

Released by Zeyuan Yang through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published183.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.