DeepSeek-R1-Distill-Qwen-1.5B-Basic / generation_config.json
leonMW's picture
Training in progress, step 100
9a12737 verified
raw
history blame contribute delete
217 Bytes
{
"_from_model_config": true,
"bos_token_id": 151646,
"do_sample": true,
"eos_token_id": [
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.57.0"
}