-
SFT stage 1: sft/new_tries/sft_enhanced_June5/sft_stage1_merged model
-
GRPO ontop of SFT model name: grpo_openr1__qwen3_maxtokens_lr2e-6_checkpoint-450_merged
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Delete .ipynb_checkpoints
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Revert to Eren 35 percent math model
-
Upload CleanHard 500-step math model
-
Delete .ipynb_checkpoints
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Delete .ipynb_checkpoints
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
initial commit