pigfoot
/

Llama-3-Taiwan-8B-Instruct-V1-4bit-AWQ

Model card Files Files and versions Community

Llama-3-Taiwan-8B-Instruct-V1-4bit-AWQ / quantize_config.json

pigfoot's picture

Upload folder using huggingface_hub

0cc8297 verified 3 months ago

95 Bytes

{"q_group_size": 128, "w_bit": 4, "zero_point": true, "version": "GEMM", "quant_method": "awq"}