freedak/law-kb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: 升级 LLM 至 Qwen3.6-35B-A3B-int4-AutoRound

Browse Source 
模型文件已在服务器 /data/models 就位，容器 qwen36 接替 qwen35 运行，
served-model-name 为 qwen3.6-35b。已验证 enable_thinking 开关与
</think> 分隔符行为一致，RAG 链路正常。

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
freedak
2026-09-21 16:34:12 +08:00
co-authored by Devin
parent 5bc69b1c23
commit 789951a42a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/config.py
+1 -1
View File
@@ -39,7 +39,7 @@ LLM_URL = os.getenv("LLM_URL", "http://localhost:7000/v1")
EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL", "qwen3-embedding-0.6b") EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL", "qwen3-embedding-0.6b")
# LLM 模型名 # LLM 模型名
LLM_MODEL = os.getenv("LLM_MODEL", "qwen3.5-35b") LLM_MODEL = os.getenv("LLM_MODEL", "qwen3.6-35b")
# ===== 索引参数 ===== # ===== 索引参数 =====
# embedding 批量大小 # embedding 批量大小