m1-32b / generation_config.json
Can111's picture
Initial upload of qwen2.5-32b-instruct_deepseek-reasoner_2004_03-10-21_lr1e-5_wd1e-4_epo5_len32768_tbs1
d55c213 verified
raw
history blame contribute delete
243 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.49.0"
}