Llama-PLLuM-8B-instruct-FP8-Dynamic / generation_config.json
cmsptcp's picture
Upload PLLuM-12B-instruct FP8 quantized model
c31f6ce verified
raw
history blame contribute delete
180 Bytes
{
"_from_model_config": true,
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": 128001,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.56.0"
}