SAVRN
Search Contact SAVRN

Open-weight model

visualrl-qwen3vl4b-ppo1-visionsr1-hires-fix

by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-visionsr1-hires-fix

visualrl-qwen3vl4b-ppo1-visionsr1-hires-fix is an open-weight model from Zeyuan Yang. Its published files total 196.5 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-visionsr1-hires-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
32e6dfca14f167b4ee6029ddd078c8a97b3cda02
First published
2026-09-18
Last updated
2026-09-20

Files and Weights

91 files, 196.5 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 · 12.7 GB
Repository1 file · 2.6 KB
Every file
FileTypeSizeSHA-256
global_step_100/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 2c03e1a65d7f
global_step_100/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB c65280b05270
global_step_100/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 6066cd8ef18c
global_step_100/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 46b5ff60e114
global_step_100/actor/model_world_size_4_rank_0.ptWeights4.8 GB 538492892c26
global_step_100/actor/model_world_size_4_rank_1.ptWeights4.8 GB a1407269120f
global_step_100/actor/model_world_size_4_rank_2.ptWeights4.8 GB f906eed0df8a
global_step_100/actor/model_world_size_4_rank_3.ptWeights4.8 GB 10e11fca3afa
global_step_100/actor/optim_world_size_4_rank_0.ptWeights8.9 GB ee5cb627d495
global_step_100/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 8fa41e775e75
global_step_100/actor/optim_world_size_4_rank_2.ptWeights8.9 GB dacbe3cfa10e
global_step_100/actor/optim_world_size_4_rank_3.ptWeights8.9 GB 458ac4b6201b
global_step_100/dataloader.ptWeights2.0 KB c42b7df3e24d
global_step_110/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB adae88af8e35
global_step_110/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 431b0146d6a7
global_step_110/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 9c8d0656584e
global_step_110/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB c6f8d7ff1214
global_step_110/actor/model_world_size_4_rank_0.ptWeights4.8 GB 66f0d477d5f0
global_step_110/actor/model_world_size_4_rank_1.ptWeights4.8 GB 0476e489bd14
global_step_110/actor/model_world_size_4_rank_2.ptWeights4.8 GB 596dd443e5c2
global_step_110/actor/model_world_size_4_rank_3.ptWeights4.8 GB bb81efa73d3b
global_step_110/actor/optim_world_size_4_rank_0.ptWeights8.9 GB 7fe8306a6aee
global_step_110/actor/optim_world_size_4_rank_1.ptWeights8.9 GB ad8fa9e8a2ee
global_step_110/actor/optim_world_size_4_rank_2.ptWeights8.9 GB 61cf3d2e1e14
global_step_110/actor/optim_world_size_4_rank_3.ptWeights8.9 GB cef37a066041
global_step_110/dataloader.ptWeights2.0 KB ed950df6a28f
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 fda46e6f1991
global_step_90/actor/model_world_size_4_rank_1.ptWeights4.8 GB d698cead7e97
global_step_90/actor/model_world_size_4_rank_2.ptWeights4.8 GB 9b06742fb975
global_step_90/actor/model_world_size_4_rank_3.ptWeights4.8 GB db03aef227f7
global_step_90/actor/optim_world_size_4_rank_0.ptWeights8.9 GB b378b6008c04
global_step_90/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 4eebf04de46f
global_step_90/actor/optim_world_size_4_rank_2.ptWeights8.9 GB f7b5792b1366
global_step_90/actor/optim_world_size_4_rank_3.ptWeights8.9 GB 1a4767dca892
global_step_90/dataloader.ptWeights2.0 KB 3a26c38a809f
global_step_90_highlight/actor/model_world_size_4_rank_0.ptWeights4.8 GB fda46e6f1991
global_step_90_highlight/actor/model_world_size_4_rank_1.ptWeights4.8 GB d698cead7e97
global_step_90_highlight/actor/model_world_size_4_rank_2.ptWeights4.8 GB 9b06742fb975
global_step_90_highlight/actor/model_world_size_4_rank_3.ptWeights4.8 GB db03aef227f7
global_step_90_highlight/dataloader.ptWeights2.0 KB 3a26c38a809f
global_step_100/actor/huggingface/added_tokens.jsonConfiguration707 B
global_step_100/actor/huggingface/config.jsonConfiguration1.6 KB
global_step_100/actor/huggingface/generation_config.jsonConfiguration213 B
global_step_100/actor/huggingface/preprocessor_config.jsonConfiguration782 B
global_step_100/actor/huggingface/special_tokens_map.jsonConfiguration613 B
global_step_100/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B
global_step_110/actor/huggingface/added_tokens.jsonConfiguration707 B
global_step_110/actor/huggingface/config.jsonConfiguration1.6 KB
global_step_110/actor/huggingface/generation_config.jsonConfiguration213 B
global_step_110/actor/huggingface/preprocessor_config.jsonConfiguration782 B
global_step_110/actor/huggingface/special_tokens_map.jsonConfiguration613 B
global_step_110/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_100/actor/huggingface/chat_template.jinjaOther5.3 KB
global_step_110/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_vsr1_hires.logOther12.7 GB fd7c98f5fde7
train_logs/train_metrics_q3vl4b_ppo1_vsr1_hires.jsonlOther249.0 KB
.gitattributesRepository2.6 KB
global_step_100/actor/huggingface/merges.txtTokenizer1.7 MB
global_step_100/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_100/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB
global_step_100/actor/huggingface/vocab.jsonTokenizer2.8 MB
global_step_110/actor/huggingface/merges.txtTokenizer1.7 MB
global_step_110/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_110/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB
global_step_110/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.