utahnlp/llama2_7b_sparsegpt_0.5_tulu2_sft_16gpu_bs128_sumloss_sparse_deepspeed Text Generation • Updated 28 days ago • 3
utahnlp/llama2_7b_magnitude_0.5_tulu2_sft_16gpu_bs128_sumloss_sparse_deepspeed Text Generation • Updated 28 days ago • 3