github/microsoft-SkillOpt
1
0
Fork 0
mirror of https://github.com/microsoft/SkillOpt.git synced 2026-07-03 14:02:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(eval-only): call configure_qwen_chat so itslocal LLM endpoints can be used

Browse Source 
The eval-only tool skipped configuring some of the backend types, that
the training did configure. Because of this, the eval is silently
fell back to a local endpoint that wasn't actually configured, and
all evaluations runs failed.

Replicate the backend setup based on the trainer's code, and eval-only
can run with the qwen_chat backends.

Co-authored-by: Qwen-Coder <noreply@qwen.ai>
This commit is contained in:
Gergely Imreh
2026-06-24 15:00:56 +08:00
parent 2d7e37a395
commit 8559308361
1 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
scripts/eval_only.py
View File

@@ -28,6 +28,7 @@ from skillopt.model import (
configure_azure_openai,
configure_claude_code_exec,
configure_codex_exec,
configure_qwen_chat,
set_reasoning_effort,
set_target_backend,
set_target_deployment,
@@ -401,6 +402,20 @@ def main() -> None:
effort=cfg.get("claude_code_exec_effort", cfg.get("reasoning_effort", "medium")),
max_thinking_tokens=cfg.get("claude_code_exec_max_thinking_tokens", 16384),
)
configure_qwen_chat(
base_url=cfg.get("qwen_chat_base_url") or None,
api_key=cfg.get("qwen_chat_api_key") or None,
temperature=cfg.get("qwen_chat_temperature"),
timeout_seconds=cfg.get("qwen_chat_timeout_seconds"),
max_tokens=cfg.get("qwen_chat_max_tokens"),
enable_thinking=cfg.get("qwen_chat_enable_thinking"),
target_base_url=cfg.get("target_qwen_chat_base_url") or None,
target_api_key=cfg.get("target_qwen_chat_api_key") or None,
target_temperature=cfg.get("target_qwen_chat_temperature"),
target_timeout_seconds=cfg.get("target_qwen_chat_timeout_seconds"),
target_max_tokens=cfg.get("target_qwen_chat_max_tokens"),
target_enable_thinking=cfg.get("target_qwen_chat_enable_thinking"),
)
set_reasoning_effort(cfg.get("reasoning_effort", "") or None)
# Build adapter