Files
deepseek-R1-0528-Qwen3-8b-l…/generation_config.json
ModelHub XC 151ce2efef 初始化项目,由ModelHub XC社区提供模型
Model: bcoding/deepseek-R1-0528-Qwen3-8b-llvm-sft-trained-16bit-epoch-1
Source: Original Platform
2026-09-20 18:11:19 +08:00

9 lines
171 B
JSON

{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151645,
"max_length": 131072,
"pad_token_id": 151654,
"transformers_version": "4.57.6"
}