Skip to page content
SAVRN
Search Plan a project

Open-weight model

visualrl-qwen3vl2b-ppo1-4cx-c10-clean

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

visualrl-qwen3vl2b-ppo1-4cx-c10-clean is an open-weight model from Zeyuan Yang. Its published files total 30.8 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-ppo1-4cx-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
787726d51d27316b7747edc17cf0d2c34305ef03
First published
2026-09-23
Last updated
2026-09-24

Files and Weights

182 files, 30.8 GB in total. The weights are 3 files totalling 14.6 GB in safetensors.

Weights3 files · 14.6 GB
Configuration112 files · 328.5 MB
Tokenizer12 files · 47.6 MB
Other54 files · 15.8 GB
Repository1 file · 3.1 KB
Every file
FileTypeSizeSHA-256
global_step_180_merged/model.safetensorsWeights4.9 GB 502256d776e0
global_step_270_merged/model.safetensorsWeights4.9 GB ef1f89b0b747
global_step_90_merged/model.safetensorsWeights4.9 GB cb1c05746d5e
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/blink_output.jsonConfiguration9.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/chartqa_output.jsonConfiguration2.5 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/chartqa_scores.jsonConfiguration193 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/hallusionbench_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/hallusionbench_scores.jsonConfiguration489 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/logicvista_output.jsonConfiguration4.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/logicvista_scores.jsonConfiguration501 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathverse_output.jsonConfiguration21.1 MB 28a7a16193dc
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathverse_scores.jsonConfiguration2.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvision_output.jsonConfiguration4.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvision_scores.jsonConfiguration8.8 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvista_output.jsonConfiguration5.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvista_scores.jsonConfiguration7.5 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmbench_output.jsonConfiguration13.1 MB 32aef32c719e
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmbench_scores.jsonConfiguration6.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mme_output.jsonConfiguration2.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu_output.jsonConfiguration6.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu_pro_output.jsonConfiguration196.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu_pro_scores.jsonConfiguration110 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu_scores.jsonConfiguration2.6 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmstar_output.jsonConfiguration6.7 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmvet_output.jsonConfiguration281.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmvet_scores.jsonConfiguration516 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/perceptionbench_output.jsonConfiguration24.0 MB 6d404848d467
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/perceptionbench_scores.jsonConfiguration1.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/realworldqa_output.jsonConfiguration1.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/realworldqa_scores.jsonConfiguration95 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/scienceqa_output.jsonConfiguration5.7 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/scienceqa_scores.jsonConfiguration359 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/visnumbench_output.jsonConfiguration11.8 MB 46b502db7e88
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/visnumbench_scores.jsonConfiguration950 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/blink_output.jsonConfiguration8.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/chartqa_output.jsonConfiguration2.5 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/chartqa_scores.jsonConfiguration193 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/hallusionbench_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/hallusionbench_scores.jsonConfiguration494 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/logicvista_output.jsonConfiguration3.6 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/logicvista_scores.jsonConfiguration488 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mathvista_output.jsonConfiguration5.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mathvista_scores.jsonConfiguration7.5 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmbench_output.jsonConfiguration11.6 MB a306a54b71cc
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmbench_scores.jsonConfiguration6.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mme_output.jsonConfiguration3.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmstar_output.jsonConfiguration5.6 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmvet_output.jsonConfiguration265.8 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmvet_scores.jsonConfiguration503 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/perceptionbench_output.jsonConfiguration22.3 MB 9a5669b3c2b7
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/perceptionbench_scores.jsonConfiguration1.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/realworldqa_output.jsonConfiguration1.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/realworldqa_scores.jsonConfiguration95 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/scienceqa_output.jsonConfiguration5.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/scienceqa_scores.jsonConfiguration357 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/visnumbench_output.jsonConfiguration11.4 MB 5e7653d7c973
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/visnumbench_scores.jsonConfiguration938 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/blink_output.jsonConfiguration9.0 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/blink_scores.jsonConfiguration3.2 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/chartqa_output.jsonConfiguration2.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/chartqa_scores.jsonConfiguration193 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/hallusionbench_output.jsonConfiguration2.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/hallusionbench_scores.jsonConfiguration491 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/logicvista_output.jsonConfiguration4.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/logicvista_scores.jsonConfiguration502 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathverse_output.jsonConfiguration24.3 MB 1c4ac8380418
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathverse_scores.jsonConfiguration2.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvision_output.jsonConfiguration4.1 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvision_scores.jsonConfiguration8.8 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvista_output.jsonConfiguration5.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvista_scores.jsonConfiguration7.5 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmbench_output.jsonConfiguration12.9 MB 71f8989036ea
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmbench_scores.jsonConfiguration6.4 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mme_output.jsonConfiguration2.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mme_scores.jsonConfiguration2.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu_output.jsonConfiguration6.2 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu_pro_output.jsonConfiguration196.3 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu_pro_scores.jsonConfiguration108 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu_scores.jsonConfiguration2.7 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmstar_output.jsonConfiguration6.4 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmstar_scores.jsonConfiguration3.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmvet_output.jsonConfiguration233.1 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmvet_scores.jsonConfiguration503 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/perceptionbench_output.jsonConfiguration25.0 MB 8e099974d27f
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/perceptionbench_scores.jsonConfiguration1.0 KB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/realworldqa_output.jsonConfiguration1.3 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/realworldqa_scores.jsonConfiguration95 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/scienceqa_output.jsonConfiguration5.8 MB —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/scienceqa_scores.jsonConfiguration358 B —
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/visnumbench_output.jsonConfiguration11.9 MB 70a91e11e5e7
eval_results/visualrl-qwen3vl2b-ppo1-4cx-c10-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/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_4cx_c10.logOther15.8 GB 26366cce8c8d
logs/eval-visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm.logOther1.6 MB —
logs/eval-visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm.logOther1.6 MB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/blink.logOther144.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/chartqa.logOther100.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/hallusionbench.logOther49.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/logicvista.logOther34.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathverse.logOther206.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvision.logOther26.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mathvista.logOther60.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmbench.logOther160.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mme.logOther104.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu.logOther84.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmmu_pro.logOther118.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmstar.logOther76.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/mmvet.logOther45.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/perceptionbench.logOther185.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/realworldqa.logOther56.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/scienceqa.logOther86.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s180-vllm/visnumbench.logOther87.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/blink.logOther144.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/chartqa.logOther101.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/hallusionbench.logOther51.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/logicvista.logOther35.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mathvista.logOther61.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmbench.logOther160.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mme.logOther106.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmstar.logOther77.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/mmvet.logOther45.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/perceptionbench.logOther195.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/realworldqa.logOther58.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/scienceqa.logOther85.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s270-vllm/visnumbench.logOther93.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/blink.logOther143.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/chartqa.logOther96.3 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/hallusionbench.logOther50.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/logicvista.logOther33.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathverse.logOther195.8 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvision.logOther27.1 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mathvista.logOther61.4 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmbench.logOther161.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mme.logOther102.9 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu.logOther82.6 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmmu_pro.logOther116.7 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmstar.logOther74.2 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/mmvet.logOther45.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/perceptionbench.logOther183.0 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/realworldqa.logOther59.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/scienceqa.logOther86.5 KB —
logs/visualrl-qwen3vl2b-ppo1-4cx-c10-clean-s90-vllm/visnumbench.logOther87.2 KB —
train_logs/train_metrics_q3vl2b_ppo1_4cx_c10.jsonlOther542.0 KB —
.gitattributesRepository3.1 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.