---
license: apache-2.0
tags:
  - cookxpert
  - mlc-llm
  - web-llm
  - cooking
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
library_name: mlc-llm
---

# CookXpert Chef 1.7B (MLC)

CookXpert chef fine-tune **MLC bundle** for on-device WebGPU inference.

Weights are mirrored from [mlc-ai/SmolLM2-1.7B-Instruct-q4f16_1-MLC](https://huggingface.co/mlc-ai/SmolLM2-1.7B-Instruct-q4f16_1-MLC) until custom LoRA MLC artifacts are uploaded.
The app applies CookXpert chef system prompts on top of these weights.

## Replace with custom fine-tune

```bash
export HF_TOKEN=hf_...
python ml/cookxpert_chef_ft/publish_to_hf.py --config ml/cookxpert_chef_ft/config.gpu.yaml --create-repo
```

When `mlc-chat-config.json` and wasm weights in this repo match your build, CookXpert shows **Weights live**.