SAVRN
Search Contact SAVRN

Open-weight model

visualrl-qwen3vl4b-ppo1-ral-c005-r2-fix

by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-ral-c005-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-c005-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
75fbda447cf1b7ea285fe66a3614631aead635f9
First published
2026-09-17
Last updated
2026-09-18

Files and Weights

131 files, 183.8 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 · 3.2 MB
Repository1 file · 3.0 KB
Every file
FileTypeSizeSHA-256
global_step_150/actor/extra_state_world_size_8_rank_0.ptWeights15.1 KB 2c5dddc72ee9
global_step_150/actor/extra_state_world_size_8_rank_1.ptWeights15.1 KB 3a37e5b8768b
global_step_150/actor/extra_state_world_size_8_rank_2.ptWeights15.1 KB 0bcf3c113b1c
global_step_150/actor/extra_state_world_size_8_rank_3.ptWeights15.1 KB 5a3f87905f41
global_step_150/actor/extra_state_world_size_8_rank_4.ptWeights15.1 KB 99d4ae9f9f37
global_step_150/actor/extra_state_world_size_8_rank_5.ptWeights15.1 KB 47cf8b2f8770
global_step_150/actor/extra_state_world_size_8_rank_6.ptWeights15.1 KB f32c43171bff
global_step_150/actor/extra_state_world_size_8_rank_7.ptWeights15.1 KB 457292fccacd
global_step_150/actor/model_world_size_8_rank_0.ptWeights2.4 GB 246849f81b50
global_step_150/actor/model_world_size_8_rank_1.ptWeights2.4 GB da8a57e984eb
global_step_150/actor/model_world_size_8_rank_2.ptWeights2.4 GB e00d039936b2
global_step_150/actor/model_world_size_8_rank_3.ptWeights2.4 GB 7e2a59e81969
global_step_150/actor/model_world_size_8_rank_4.ptWeights2.4 GB a731fa7c14ea
global_step_150/actor/model_world_size_8_rank_5.ptWeights2.4 GB b1f18402de3e
global_step_150/actor/model_world_size_8_rank_6.ptWeights2.4 GB 72e2bf79f88d
global_step_150/actor/model_world_size_8_rank_7.ptWeights2.4 GB 46a735421ea3
global_step_150/actor/optim_world_size_8_rank_0.ptWeights4.4 GB 569bff83c008
global_step_150/actor/optim_world_size_8_rank_1.ptWeights4.4 GB b01b7f1e70cb
global_step_150/actor/optim_world_size_8_rank_2.ptWeights4.4 GB edee908a73ba
global_step_150/actor/optim_world_size_8_rank_3.ptWeights4.4 GB 2d1232aeb5ec
global_step_150/actor/optim_world_size_8_rank_4.ptWeights4.4 GB 65eaf0aaa7a9
global_step_150/actor/optim_world_size_8_rank_5.ptWeights4.4 GB 2d4c0d45fa0c
global_step_150/actor/optim_world_size_8_rank_6.ptWeights4.4 GB 8139500f86d6
global_step_150/actor/optim_world_size_8_rank_7.ptWeights4.4 GB 0b0a0318ffe4
global_step_150/dataloader.ptWeights2.0 KB 54bc2ce1ae85
global_step_160/actor/extra_state_world_size_8_rank_0.ptWeights15.1 KB 13db9c675d16
global_step_160/actor/extra_state_world_size_8_rank_1.ptWeights15.1 KB ba3f44255501
global_step_160/actor/extra_state_world_size_8_rank_2.ptWeights15.1 KB 8550c03f4b70
global_step_160/actor/extra_state_world_size_8_rank_3.ptWeights15.1 KB d5c842691e3b
global_step_160/actor/extra_state_world_size_8_rank_4.ptWeights15.1 KB 6318988ea7c9
global_step_160/actor/extra_state_world_size_8_rank_5.ptWeights15.1 KB ab3b4dad2f1d
global_step_160/actor/extra_state_world_size_8_rank_6.ptWeights15.1 KB 62018e1ac066
global_step_160/actor/extra_state_world_size_8_rank_7.ptWeights15.1 KB 4efeec55bac0
global_step_160/actor/model_world_size_8_rank_0.ptWeights2.4 GB c03f70756887
global_step_160/actor/model_world_size_8_rank_1.ptWeights2.4 GB f2a0c22172c4
global_step_160/actor/model_world_size_8_rank_2.ptWeights2.4 GB 4ed68daa28b2
global_step_160/actor/model_world_size_8_rank_3.ptWeights2.4 GB e5bfe19e8a81
global_step_160/actor/model_world_size_8_rank_4.ptWeights2.4 GB 19edc329aff5
global_step_160/actor/model_world_size_8_rank_5.ptWeights2.4 GB 19c0dad3688c
global_step_160/actor/model_world_size_8_rank_6.ptWeights2.4 GB 97c2cd222465
global_step_160/actor/model_world_size_8_rank_7.ptWeights2.4 GB 5e137021ccca
global_step_160/actor/optim_world_size_8_rank_0.ptWeights4.4 GB ea32e5b1fc7f
global_step_160/actor/optim_world_size_8_rank_1.ptWeights4.4 GB 6a632c17a04a
global_step_160/actor/optim_world_size_8_rank_2.ptWeights4.4 GB a45f9ba81074
global_step_160/actor/optim_world_size_8_rank_3.ptWeights4.4 GB aa28620374d6
global_step_160/actor/optim_world_size_8_rank_4.ptWeights4.4 GB 7d3ebebbea88
global_step_160/actor/optim_world_size_8_rank_5.ptWeights4.4 GB 1f19e02b0cf5
global_step_160/actor/optim_world_size_8_rank_6.ptWeights4.4 GB c3271c9a2d58
global_step_160/actor/optim_world_size_8_rank_7.ptWeights4.4 GB 653e98606e37
global_step_160/dataloader.ptWeights2.0 KB 50a57353a5fa
global_step_90/actor/extra_state_world_size_8_rank_0.ptWeights15.1 KB 760f13a304a9
global_step_90/actor/extra_state_world_size_8_rank_1.ptWeights15.1 KB 83acfe9c6fac
global_step_90/actor/extra_state_world_size_8_rank_2.ptWeights15.1 KB 181d82b502f4
global_step_90/actor/extra_state_world_size_8_rank_3.ptWeights15.1 KB 1a9e29da286b
global_step_90/actor/extra_state_world_size_8_rank_4.ptWeights15.1 KB d0724d72ee50
global_step_90/actor/extra_state_world_size_8_rank_5.ptWeights15.1 KB b7e69923a7e6
global_step_90/actor/extra_state_world_size_8_rank_6.ptWeights15.1 KB 039cb36a9643
global_step_90/actor/extra_state_world_size_8_rank_7.ptWeights15.1 KB 968346d925d6
global_step_90/actor/model_world_size_8_rank_0.ptWeights2.4 GB 0509ab8b0341
global_step_90/actor/model_world_size_8_rank_1.ptWeights2.4 GB 9c49aa9d53a6
global_step_90/actor/model_world_size_8_rank_2.ptWeights2.4 GB 3d79b8c351ec
global_step_90/actor/model_world_size_8_rank_3.ptWeights2.4 GB 0403de2e1db6
global_step_90/actor/model_world_size_8_rank_4.ptWeights2.4 GB c8d001723ab9
global_step_90/actor/model_world_size_8_rank_5.ptWeights2.4 GB 36008e3f35df
global_step_90/actor/model_world_size_8_rank_6.ptWeights2.4 GB 092679585762
global_step_90/actor/model_world_size_8_rank_7.ptWeights2.4 GB c777c1c6b79d
global_step_90/actor/optim_world_size_8_rank_0.ptWeights4.4 GB 7ace0099d953
global_step_90/actor/optim_world_size_8_rank_1.ptWeights4.4 GB 92991dc9d886
global_step_90/actor/optim_world_size_8_rank_2.ptWeights4.4 GB 620e84c7bbc0
global_step_90/actor/optim_world_size_8_rank_3.ptWeights4.4 GB 902e6a1dc0ff
global_step_90/actor/optim_world_size_8_rank_4.ptWeights4.4 GB 500bb361f2b5
global_step_90/actor/optim_world_size_8_rank_5.ptWeights4.4 GB 80926575bfd5
global_step_90/actor/optim_world_size_8_rank_6.ptWeights4.4 GB 9d989c681f81
global_step_90/actor/optim_world_size_8_rank_7.ptWeights4.4 GB 16fb2f522708
global_step_90/dataloader.ptWeights2.0 KB eeaaa0e26260
global_step_90_highlight/actor/model_world_size_8_rank_0.ptWeights2.4 GB 0509ab8b0341
global_step_90_highlight/actor/model_world_size_8_rank_1.ptWeights2.4 GB 9c49aa9d53a6
global_step_90_highlight/actor/model_world_size_8_rank_2.ptWeights2.4 GB 3d79b8c351ec
global_step_90_highlight/actor/model_world_size_8_rank_3.ptWeights2.4 GB 0403de2e1db6
global_step_90_highlight/actor/model_world_size_8_rank_4.ptWeights2.4 GB c8d001723ab9
global_step_90_highlight/actor/model_world_size_8_rank_5.ptWeights2.4 GB 36008e3f35df
global_step_90_highlight/actor/model_world_size_8_rank_6.ptWeights2.4 GB 092679585762
global_step_90_highlight/actor/model_world_size_8_rank_7.ptWeights2.4 GB c777c1c6b79d
global_step_90_highlight/dataloader.ptWeights2.0 KB eeaaa0e26260
global_step_150/actor/huggingface/added_tokens.jsonConfiguration707 B
global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB
global_step_150/actor/huggingface/generation_config.jsonConfiguration213 B
global_step_150/actor/huggingface/preprocessor_config.jsonConfiguration782 B
global_step_150/actor/huggingface/special_tokens_map.jsonConfiguration613 B
global_step_150/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B
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_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_150/actor/huggingface/chat_template.jinjaOther5.3 KB
global_step_160/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_ral_c005_r2.logOther2.8 MB f3610aff8b85
train_logs/train_metrics_q3vl4b_ppo1_ral_c005_r2.jsonlOther341.6 KB
.gitattributesRepository3.0 KB
global_step_150/actor/huggingface/merges.txtTokenizer1.7 MB
global_step_150/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_150/actor/huggingface/tokenizer_config.jsonTokenizer5.5 KB
global_step_150/actor/huggingface/vocab.jsonTokenizer2.8 MB
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_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
183.8 GB
Download from Zeyuan Yang

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

Memory Requirements

PrecisionWeights in memory
As published183.8 GB

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