LoRA for Tool Calling

Same LoRA from 07-A, higher rank (r=16), two target projections (q_proj + v_proj), and training examples formatted with Qwen3's native tool-calling template. Teach the model to emit valid JSON for a 6-function kitchen-assistant API. Evaluate deterministically: does the JSON parse? Does the function name match? Does it generalise to held-out prompts?

Time

60–90 min

Hardware

GPU · Mac · Colab · CPU

Act

VI · Making It Yours

Status

Live

Artifact

A LoRA adapter that produces valid tool-call JSON + a pass/fail eval harness.

Clone the labs repo and run this lab as a script or open it as a notebook:

git clone https://github.com/iqbal-sk/Microscale-labs.git
cd Microscale
just setup-auto      # auto-detects CPU / CUDA / Mac
just run 07-b
# or:  jupyter lab labs/07-b-lora-tool-calling/lab.py

Full install options (uv, pip, or the platform-specific CUDA paths) are in the labs README.