LLM-Models / quantize.sh
Arun Kumar Tiwary
Upload folder using huggingface_hub
ae919d8 verified
raw
history blame contribute delete
103 Bytes
./quantize ./Meta-Llama-3-8B-Instruct_fp16.bin output/Meta-Llama-3-8B-Instruct_fp16_Q4_K_M.bin Q4_K_M