Skip to content

Conversation

@nzw0301
Copy link
Contributor

@nzw0301 nzw0301 commented Jul 3, 2025

The commands to get the scores:

vllm serve Qwen/Qwen3-8B --reasoning-parser qwen3 --generation-config auto --dtype bfloat16
OPENAI_BASE_URL=http://localhost:8000/v1 OPENAI_API_KEY=dummy python3 run-openai.py --mode chat --model Qwen/Qwen3-8B --temperature 0.0 --disable-thinking
OPENAI_BASE_URL=http://localhost:8000/v1 OPENAI_API_KEY=dummy python3 run-openai.py --mode completion --model Qwen/Qwen3-8B --temperature 0.0 --disable-thinking

OPENAI_BASE_URL=http://localhost:8000/v1 OPENAI_API_KEY=dummy python3 run-openai.py --mode chat --model Qwen/Qwen3-8B --temperature 1.0 --disable-thinking
OPENAI_BASE_URL=http://localhost:8000/v1 OPENAI_API_KEY=dummy python3 run-openai.py --mode completion --model Qwen/Qwen3-8B --temperature 1.0 --disable-thinking

@imos imos changed the title Add qwen3-8b feat: add qwen3-8b Jul 3, 2025
@imos imos self-requested a review July 3, 2025 15:09
@imos imos merged commit 341f9f6 into pfnet-research:main Jul 3, 2025
1 check passed
@nzw0301 nzw0301 deleted the add-qwen-8b branch July 3, 2025 15:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants