CoolFace
Modelpublic

VerlTool/pixel_reasoner-7b-grpo-n8-b128-t1.0-lr1e-6-complex-reward-new_global_step_50

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes6downloads
root
file.gitattributes2 KBdownload
fileadded_tokens.json605 Bdownload
filechat_template.jinja1017 Bdownload
fileconfig.json3 KBdownload
filegeneration_config.json282 Bdownload
filemerges.txt1.6 MBdownload
filemodel-00001-of-00007.safetensors4.61 GBdownload
filemodel-00002-of-00007.safetensors4.64 GBdownload
filemodel-00003-of-00007.safetensors4.59 GBdownload
filemodel-00004-of-00007.safetensors4.66 GBdownload
filemodel-00005-of-00007.safetensors4.64 GBdownload
filemodel-00006-of-00007.safetensors4.59 GBdownload
filemodel-00007-of-00007.safetensors3.15 GBdownload
filemodel.safetensors.index.json56 KBdownload
filepreprocessor_config.json573 Bdownload
filespecial_tokens_map.json613 Bdownload
filetokenizer_config.json5 KBdownload
filetokenizer.json10.9 MBdownload
filevideo_preprocessor_config.json2 KBdownload
filevocab.json2.6 MBdownload

VerlTool/pixel_reasoner-7b-grpo-n8-b128-t1.0-lr1e-6-complex-reward-new_global_step_50 · main · files are served by the source, never re-hosted here