Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
cf6a0e7 verified
raw
history blame
181 Bytes
{
"_from_model_config": true,
"bos_token_id": 100000,
"do_sample": true,
"eos_token_id": 100001,
"temperature": 0.7,
"top_p": 0.95,
"transformers_version": "4.42.0"
}