Skip to page content
SAVRN
Search Plan a project

Open-weight model

visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-fix

by Zeyuan Yang Miiche/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-fix

visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-fix is an open-weight model from Zeyuan Yang. Its published files total 105.3 GB.

Parameters—
Context—
Weights90.1 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
Miiche/visualrl-qwen3vl2b-ppo1-4bx-c10-Lall-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
c156a3dd5504a1ea263998ed1b0ed6e293d9af3b
First published
2026-09-20
Last updated
2026-09-21

Files and Weights

91 files, 105.3 GB in total. The weights are 44 files totalling 90.1 GB in pt.

Weights44 files · 90.1 GB
Configuration24 files · 18.9 KB
Tokenizer16 files · 63.5 MB
Other6 files · 15.1 GB
Repository1 file · 2.7 KB
Every file
FileTypeSizeSHA-256
global_step_130/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 4d30ef564d8e
global_step_130/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 2ec9fab91593
global_step_130/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 07e643828a24
global_step_130/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB b8f6dffb2564
global_step_130/actor/model_world_size_4_rank_0.ptWeights2.4 GB acc2f96cf2cc
global_step_130/actor/model_world_size_4_rank_1.ptWeights2.4 GB af9c7031f84b
global_step_130/actor/model_world_size_4_rank_2.ptWeights2.4 GB 389bdde496f1
global_step_130/actor/model_world_size_4_rank_3.ptWeights2.4 GB c4e03c8bf133
global_step_130/actor/optim_world_size_4_rank_0.ptWeights4.3 GB 0afae0bb6e0f
global_step_130/actor/optim_world_size_4_rank_1.ptWeights4.3 GB ce7c3d4c805c
global_step_130/actor/optim_world_size_4_rank_2.ptWeights4.3 GB a2dee32530b5
global_step_130/actor/optim_world_size_4_rank_3.ptWeights4.3 GB 145e60ead65c
global_step_130/dataloader.ptWeights2.0 KB 2517e03264b5
global_step_140/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB a1971c5e05b1
global_step_140/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 469efd6a5046
global_step_140/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 79c4b91a1d88
global_step_140/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 015bf18e21ef
global_step_140/actor/model_world_size_4_rank_0.ptWeights2.4 GB b48c68add185
global_step_140/actor/model_world_size_4_rank_1.ptWeights2.4 GB b434f8357475
global_step_140/actor/model_world_size_4_rank_2.ptWeights2.4 GB 11c2ec4fbe19
global_step_140/actor/model_world_size_4_rank_3.ptWeights2.4 GB e96af38285ad
global_step_140/actor/optim_world_size_4_rank_0.ptWeights4.3 GB a4be07bcac8f
global_step_140/actor/optim_world_size_4_rank_1.ptWeights4.3 GB d46b62f67c2c
global_step_140/actor/optim_world_size_4_rank_2.ptWeights4.3 GB 05d8181ddf48
global_step_140/actor/optim_world_size_4_rank_3.ptWeights4.3 GB 78eb05bb7e80
global_step_140/dataloader.ptWeights2.0 KB b7de5b1b8875
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.ptWeights2.4 GB 010adc59fb75
global_step_90/actor/model_world_size_4_rank_1.ptWeights2.4 GB 9c53e7ba707b
global_step_90/actor/model_world_size_4_rank_2.ptWeights2.4 GB 991d03a05300
global_step_90/actor/model_world_size_4_rank_3.ptWeights2.4 GB 38f4c4e3643d
global_step_90/actor/optim_world_size_4_rank_0.ptWeights4.3 GB 145a43a54a2f
global_step_90/actor/optim_world_size_4_rank_1.ptWeights4.3 GB d03f0bfe2ad7
global_step_90/actor/optim_world_size_4_rank_2.ptWeights4.3 GB 6d2be65f2029
global_step_90/actor/optim_world_size_4_rank_3.ptWeights4.3 GB 2f4154e39e93
global_step_90/dataloader.ptWeights2.0 KB 0c1ec0cd7bab
global_step_90_highlight/actor/model_world_size_4_rank_0.ptWeights2.4 GB 010adc59fb75
global_step_90_highlight/actor/model_world_size_4_rank_1.ptWeights2.4 GB 9c53e7ba707b
global_step_90_highlight/actor/model_world_size_4_rank_2.ptWeights2.4 GB 991d03a05300
global_step_90_highlight/actor/model_world_size_4_rank_3.ptWeights2.4 GB 38f4c4e3643d
global_step_90_highlight/dataloader.ptWeights2.0 KB 0c1ec0cd7bab
global_step_130/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_130/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_130/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_130/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_130/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_130/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
global_step_140/actor/huggingface/added_tokens.jsonConfiguration707 B —
global_step_140/actor/huggingface/config.jsonConfiguration1.6 KB —
global_step_140/actor/huggingface/generation_config.jsonConfiguration213 B —
global_step_140/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
global_step_140/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
global_step_140/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_130/actor/huggingface/chat_template.jinjaOther5.3 KB —
global_step_140/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-q3vl2b_ppo1_4bx_c10_Lall.logOther15.1 GB 587b628d86da
train_logs/train_metrics_q3vl2b_ppo1_4bx_c10_Lall.jsonlOther282.4 KB —
.gitattributesRepository2.7 KB —
global_step_130/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_130/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_130/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_130/actor/huggingface/vocab.jsonTokenizer2.8 MB —
global_step_140/actor/huggingface/merges.txtTokenizer1.7 MB —
global_step_140/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_140/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB —
global_step_140/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
90.1 GB
Download from Zeyuan Yang

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

Memory Requirements

PrecisionWeights in memory
As published90.1 GB

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