Safetensors
Edaizi's picture
Add Qwen3-4B-Math-GRPO-Early-RL for A2-OPD
350f4a5 verified
Raw History Blame
214 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.6"
}