LLM-Models / run_gguf.sh
Arun Kumar Tiwary
Upload folder using huggingface_hub
89e2fdc verified
raw
history blame
281 Bytes
./main -m output/Meta-Llama-3-70B_fp16_Q3_K_S.bin -p "hi"
#./main -m output/Meta-Llama-3-8B-Instruct_fp16_Q4_K_M.bin -p "hi"
#./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
#./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
#./main -m output/converted_f16.bin -p "hi"