Qwen3-8B-UnBias-Plus-SFT-Instruct-4bit/generation_config.json at main - Qwen3-8B-UnBias-Plus-SFT-Instruct-4bit - Gitea: Git with a cup of tea

ahelkadyy/Qwen3-8B-UnBias-Plus-SFT-Instruct-4bit

Files

ModelHub XC fb23672715 初始化项目，由ModelHub XC社区提供模型

Model: ahelkadyy/Qwen3-8B-UnBias-Plus-SFT-Instruct-4bit
Source: Original Platform

2026-10-04 20:50:11 +08:00

8 lines

144 B

JSON

Raw Permalink Blame History

 {
   "_from_model_config": true,
   "eos_token_id": 151645,
   "max_length": 40960,
   "pad_token_id": 151669,
   "transformers_version": "4.57.6"
 }