proxsparse_models / Qwen2.5-14B-en_sft_final_400_lr0.0001_len4096_batch1_lambda0.2
29.6 GB
aladinggit's picture
Add Qwen2.5-14B-en_sft_final_400_lr0.0001_len4096_batch1_lambda0.2
8edfe8f verified