How good is Qwen/Qwen-2.5-7B-Instruct at tool calling? Any open-source models better at it?

#27

by Al-Abdulkarim - opened Jan 15

Jan 15

Hi everyone! 👋

I’m exploring tool calling / function calling capabilities in open-source LLMs and I’m curious about how well Qwen (especially Qwen-2.5-7B-Instruct) performs in this area.

Specifically, I’d love to know:

1️⃣ Has anyone tested Qwen or Qwen-2.5-7B-Instruct for tool calling / structured API usage?
Can it reliably output structured JSON or call external tools with schema prompts?

2️⃣ Are there benchmarks, examples, or best practices for doing tool calling with Qwen?

3️⃣ What other open-source models do people recommend that are good at tool calling?
For example: models that handle JSON responses, function schemas, or multi-step tool workflows.

4️⃣ If you’ve compared Qwen vs alternatives, what were your experiences?

nisar333

Jan 18

Use a pipeline as a high-level helper

from transformers import pipeline

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-7B-Instruct")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment