llama3.1B_8B_SQL_Finetuned_model / generation_config.json
pshashid's picture
Upload NVFP4 quantized model with FP8 KV-cache
0f97414 verified
raw
history blame contribute delete
184 Bytes
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.57.6"
}