Text Generation
Transformers
Safetensors
English
llama
biology
medical
text-generation-inference
4-bit precision
awq
medicine-chat-AWQ / quant_config.json
TheBloke's picture
AWQ model commit
9bf8beb
{
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM",
"modules_to_not_convert": null
}