kreas
/

FA_benchmarks

Model card Files Files and versions Community

FA_benchmarks / Llama-2-7b-hf-GPTQ-4bit

1 contributor

History: 2 commits

kreas's picture

Upload /Llama-2-7b-hf-GPTQ-4bit/gptq4bit_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json with huggingface_hub

2d911b5 verified 8 months ago

gptq4bit_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf-GPTQ-4bit/gptq4bit_batch_size_1_sq_len_256_new_tokens_256/benchmark_report.json with huggingface_hub 8 months ago