SAVRN
Search Contact SAVRN

Open-weight model

visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean

by Zeyuan Yang Miiche/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean

Parameters
Context
Weights29.0 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-r2-clean
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
d5462fe7868be35e90f7b6a406d7f2841d28483e
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

63 files, 37.3 GB in total. The weights are 6 files totalling 29.0 GB in safetensors.

Weights6 files · 29.0 GB
Configuration33 files · 18.1 MB
Tokenizer12 files · 47.6 MB
Other11 files · 8.2 GB
Repository1 file · 1.8 KB
Every file
FileTypeSizeSHA-256
global_step_180_merged/model-00001-of-00002.safetensorsWeights5.0 GB f01abfbe3875
global_step_180_merged/model-00002-of-00002.safetensorsWeights4.7 GB 688d2d301a14
global_step_270_merged/model-00001-of-00002.safetensorsWeights5.0 GB a3b2a4078483
global_step_270_merged/model-00002-of-00002.safetensorsWeights4.7 GB 65c18b841c76
global_step_90_merged/model-00001-of-00002.safetensorsWeights5.0 GB 10d67c7d066c
global_step_90_merged/model-00002-of-00002.safetensorsWeights4.7 GB 058fcdf4ed3f
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/chartqa_output.jsonConfiguration2.6 MB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/chartqa_scores.jsonConfiguration193 B
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/logicvista_output.jsonConfiguration2.6 MB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/logicvista_scores.jsonConfiguration506 B
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmbench_output.jsonConfiguration7.1 MB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmbench_scores.jsonConfiguration6.3 KB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmvet_output.jsonConfiguration214.7 KB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmvet_scores.jsonConfiguration514 B
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/realworldqa_output.jsonConfiguration887.1 KB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/realworldqa_scores.jsonConfiguration95 B
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/visnumbench_output.jsonConfiguration4.5 MB
eval_results/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/visnumbench_scores.jsonConfiguration952 B
global_step_180_merged/added_tokens.jsonConfiguration707 B
global_step_180_merged/config.jsonConfiguration1.6 KB
global_step_180_merged/generation_config.jsonConfiguration147 B
global_step_180_merged/model.safetensors.index.jsonConfiguration64.8 KB
global_step_180_merged/preprocessor_config.jsonConfiguration782 B
global_step_180_merged/special_tokens_map.jsonConfiguration613 B
global_step_180_merged/video_preprocessor_config.jsonConfiguration817 B
global_step_270_merged/added_tokens.jsonConfiguration707 B
global_step_270_merged/config.jsonConfiguration1.6 KB
global_step_270_merged/generation_config.jsonConfiguration147 B
global_step_270_merged/model.safetensors.index.jsonConfiguration64.8 KB
global_step_270_merged/preprocessor_config.jsonConfiguration782 B
global_step_270_merged/special_tokens_map.jsonConfiguration613 B
global_step_270_merged/video_preprocessor_config.jsonConfiguration817 B
global_step_90_merged/added_tokens.jsonConfiguration707 B
global_step_90_merged/config.jsonConfiguration1.6 KB
global_step_90_merged/generation_config.jsonConfiguration147 B
global_step_90_merged/model.safetensors.index.jsonConfiguration64.8 KB
global_step_90_merged/preprocessor_config.jsonConfiguration782 B
global_step_90_merged/special_tokens_map.jsonConfiguration613 B
global_step_90_merged/video_preprocessor_config.jsonConfiguration817 B
global_step_180_merged/chat_template.jinjaOther5.3 KB
global_step_270_merged/chat_template.jinjaOther5.3 KB
global_step_90_merged/chat_template.jinjaOther5.3 KB
logs/eval-train-q3vl4b_ppo1_visionsr1_r2.logOther8.2 GB cdb46a59f32d
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/chartqa.logOther107.6 KB
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/logicvista.logOther49.1 KB
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmbench.logOther170.7 KB
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/mmvet.logOther168.6 KB
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/realworldqa.logOther60.4 KB
logs/visualrl-qwen3vl4b-ppo1-visionsr1-r2-clean-s90-vllm/visnumbench.logOther160.7 KB
train_logs/train_metrics_q3vl4b_ppo1_visionsr1_r2.jsonlOther609.0 KB
.gitattributesRepository1.8 KB
global_step_180_merged/merges.txtTokenizer1.7 MB
global_step_180_merged/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_180_merged/tokenizer_config.jsonTokenizer5.5 KB
global_step_180_merged/vocab.jsonTokenizer2.8 MB
global_step_270_merged/merges.txtTokenizer1.7 MB
global_step_270_merged/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_270_merged/tokenizer_config.jsonTokenizer5.5 KB
global_step_270_merged/vocab.jsonTokenizer2.8 MB
global_step_90_merged/merges.txtTokenizer1.7 MB
global_step_90_merged/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
global_step_90_merged/tokenizer_config.jsonTokenizer5.5 KB
global_step_90_merged/vocab.jsonTokenizer2.8 MB

License and Download

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

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

Memory Requirements

PrecisionWeights in memory
As published29.0 GB

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