Llama-3.3-70B-Instruct-AWQ-4bit / generation_config.json
chuanli-lambda's picture
Initial upload of quantized model
d9f3dda verified
raw
history blame
184 Bytes
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.46.3"
}