llama-3_1-8b-instruct-ov-int4 / generation_config.json
jojo1899's picture
Improved quantization using Openvino 2024.5.0rc1
9fbf3ab
raw
history blame contribute delete
196 Bytes
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.46.2"
}