danieldk
/

Llama-3.1-8B-w4a16-int-24

compressed-tensors

Model card Files Files and versions Community

Llama-3.1-8B-w4a16-int-24 / tokenizer_config.json

Commit History

Add nm-testing/Llama-3_1-8B_2of4_w4a16_gsm8k_256_8196_damp0_1_mse_llm_compressor

04b05ee
verified

danieldk HF staff commited on Nov 19