Skip to page content
SAVRN
Search Plan a project

Open-weight model

visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean

by Zeyuan Yang Miiche/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean

visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean is an open-weight model from Zeyuan Yang. Its published files total 33.0 GB.

Parameters—
Context—
Weights14.6 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-all-c10-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
88f6fc81049e71447229e697bc1588b631a0d501
First published
2026-09-21
Last updated
2026-09-22

Files and Weights

188 files, 33.0 GB in total. The weights are 3 files totalling 14.6 GB in safetensors.

Weights3 files · 14.6 GB
Configuration116 files · 336.7 MB
Tokenizer12 files · 47.6 MB
Other56 files · 18.0 GB
Repository1 file · 3.2 KB
Every file
FileTypeSizeSHA-256
global_step_180_merged/model.safetensorsWeights4.9 GB c96e6df481a8
global_step_270_merged/model.safetensorsWeights4.9 GB aa2abce87e2c
global_step_90_merged/model.safetensorsWeights4.9 GB 331ab499787f
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/blink_output.jsonConfiguration8.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/chartqa_output.jsonConfiguration2.5 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/chartqa_scores.jsonConfiguration193 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/hallusionbench_output.jsonConfiguration2.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/hallusionbench_scores.jsonConfiguration494 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/logicvista_output.jsonConfiguration4.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/logicvista_scores.jsonConfiguration501 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathverse_output.jsonConfiguration22.6 MB f155e347d655
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathverse_scores.jsonConfiguration2.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvision_output.jsonConfiguration3.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvision_scores.jsonConfiguration8.8 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvista_output.jsonConfiguration5.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvista_scores.jsonConfiguration7.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmbench_output.jsonConfiguration12.0 MB da9141b19f6c
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmbench_scores.jsonConfiguration6.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mme_output.jsonConfiguration3.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu_output.jsonConfiguration5.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu_pro_output.jsonConfiguration196.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu_pro_scores.jsonConfiguration110 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu_scores.jsonConfiguration2.7 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmstar_output.jsonConfiguration6.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmvet_output.jsonConfiguration216.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmvet_scores.jsonConfiguration492 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/perceptionbench_output.jsonConfiguration21.1 MB 32435a28f875
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/perceptionbench_scores.jsonConfiguration1.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/realworldqa_output.jsonConfiguration1.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/realworldqa_scores.jsonConfiguration95 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/scienceqa_output.jsonConfiguration4.9 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/scienceqa_scores.jsonConfiguration359 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/visnumbench_output.jsonConfiguration11.0 MB 5abf065304a5
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/visnumbench_scores.jsonConfiguration951 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/blink_output.jsonConfiguration8.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/chartqa_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/chartqa_scores.jsonConfiguration191 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/hallusionbench_output.jsonConfiguration1.9 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/hallusionbench_scores.jsonConfiguration494 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/logicvista_output.jsonConfiguration3.6 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/logicvista_scores.jsonConfiguration488 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathverse_output.jsonConfiguration19.0 MB 64e7e5cc501b
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathverse_scores.jsonConfiguration2.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathvista_output.jsonConfiguration4.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathvista_scores.jsonConfiguration7.5 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmbench_output.jsonConfiguration11.2 MB 8f61fdec86a3
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmbench_scores.jsonConfiguration6.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mme_output.jsonConfiguration2.9 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmmu_output.jsonConfiguration5.5 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmmu_scores.jsonConfiguration2.6 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmstar_output.jsonConfiguration5.5 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmvet_output.jsonConfiguration239.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmvet_scores.jsonConfiguration493 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/perceptionbench_output.jsonConfiguration19.6 MB d521c1d91649
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/perceptionbench_scores.jsonConfiguration1.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/realworldqa_output.jsonConfiguration1.0 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/realworldqa_scores.jsonConfiguration95 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/scienceqa_output.jsonConfiguration4.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/scienceqa_scores.jsonConfiguration359 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/visnumbench_output.jsonConfiguration10.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/visnumbench_scores.jsonConfiguration950 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/blink_output.jsonConfiguration8.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/chartqa_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/chartqa_scores.jsonConfiguration193 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/hallusionbench_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/hallusionbench_scores.jsonConfiguration494 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/logicvista_output.jsonConfiguration4.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/logicvista_scores.jsonConfiguration503 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathverse_output.jsonConfiguration24.6 MB d548f5887837
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathverse_scores.jsonConfiguration2.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvision_output.jsonConfiguration4.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvision_scores.jsonConfiguration8.8 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvista_output.jsonConfiguration5.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvista_scores.jsonConfiguration7.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmbench_output.jsonConfiguration13.1 MB 971af8c2a26b
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmbench_scores.jsonConfiguration6.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mme_output.jsonConfiguration2.9 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu_output.jsonConfiguration6.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu_pro_output.jsonConfiguration196.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu_pro_scores.jsonConfiguration110 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu_scores.jsonConfiguration2.7 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmstar_output.jsonConfiguration6.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmvet_output.jsonConfiguration242.5 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmvet_scores.jsonConfiguration526 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/perceptionbench_output.jsonConfiguration23.3 MB d2438c4500eb
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/perceptionbench_scores.jsonConfiguration1.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/realworldqa_output.jsonConfiguration1.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/realworldqa_scores.jsonConfiguration94 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/scienceqa_output.jsonConfiguration5.9 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/scienceqa_scores.jsonConfiguration359 B —
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/visnumbench_output.jsonConfiguration11.2 MB cf305a6270b4
eval_results/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/visnumbench_scores.jsonConfiguration954 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/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/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/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-q3vl2b_ppo1_4bx_all_c10.logOther18.0 GB d22494e981e9
logs/eval-visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm.logOther2.2 MB —
logs/eval-visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm.logOther2.2 MB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/blink.logOther185.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/chartqa.logOther148.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/hallusionbench.logOther68.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/logicvista.logOther42.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathverse.logOther265.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvision.logOther31.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mathvista.logOther86.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmbench.logOther244.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mme.logOther145.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu.logOther100.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmmu_pro.logOther160.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmstar.logOther104.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/mmvet.logOther51.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/perceptionbench.logOther272.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/realworldqa.logOther74.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/scienceqa.logOther127.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s180-vllm/visnumbench.logOther113.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/blink.logOther187.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/chartqa.logOther144.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/hallusionbench.logOther68.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/logicvista.logOther46.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathverse.logOther279.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mathvista.logOther88.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmbench.logOther246.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mme.logOther152.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmmu.logOther107.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmstar.logOther107.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/mmvet.logOther52.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/perceptionbench.logOther282.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/realworldqa.logOther71.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/scienceqa.logOther126.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s270-vllm/visnumbench.logOther124.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/blink.logOther187.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/chartqa.logOther142.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/hallusionbench.logOther65.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/logicvista.logOther38.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathverse.logOther253.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvision.logOther27.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mathvista.logOther84.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmbench.logOther245.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mme.logOther144.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu.logOther101.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmmu_pro.logOther154.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmstar.logOther102.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/mmvet.logOther52.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/perceptionbench.logOther261.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/realworldqa.logOther75.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/scienceqa.logOther123.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4bx-all-c10-clean-s90-vllm/visnumbench.logOther115.9 KB —
train_logs/train_metrics_q3vl2b_ppo1_4bx_all_c10.jsonlOther543.0 KB —
.gitattributesRepository3.2 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
14.6 GB
Download from Zeyuan Yang

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

Memory Requirements

PrecisionWeights in memory
As published14.6 GB

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