OpenSourceRonin's picture
Upload model Meta-Llama-3.1-405B-Instruct-v16-k65536-65536-woft
81a0737 verified
raw
history blame contribute delete
230 Bytes
{
"attn_implementation": "flash_attention_2",
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.45.1"
}