Instructions to use yichengchen24/DataChef-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yichengchen24/DataChef-32B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yichengchen24/DataChef-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yichengchen24/DataChef-32B")
model = AutoModelForCausalLM.from_pretrained("yichengchen24/DataChef-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yichengchen24/DataChef-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yichengchen24/DataChef-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yichengchen24/DataChef-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yichengchen24/DataChef-32B

SGLang

How to use yichengchen24/DataChef-32B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yichengchen24/DataChef-32B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yichengchen24/DataChef-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yichengchen24/DataChef-32B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yichengchen24/DataChef-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yichengchen24/DataChef-32B with Docker Model Runner:
```
docker model run hf.co/yichengchen24/DataChef-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DataChef-32B

HF Models | HF Demo | Paper | GitHub

DataChef-32B is a specialized large language model designed for automated data recipe generation. It was introduced in the paper DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning.

DataChef-32B facilitates LLM adaptation by generating executable data processing pipelines (data recipes) that transform raw data sources into high-quality training corpora targeted at specific benchmarks.

Model Description

DataChef-32B addresses the manual, labor-intensive process of designing data processing pipelines. It was trained using online reinforcement learning with a proxy reward system that predicts downstream performance for candidate recipes. Given a target benchmark and available data sources, the model outputs a complete data recipe to adapt a base LLM.

Performance Highlights

Across diverse tasks, DataChef-32B produces practical recipes that reach performance comparable to those curated by human experts. Notably, a recipe generated by DataChef-32B was used to adapt Qwen3-1.7B-Base to the math domain, achieving a score of 66.7 on AIME'25, surpassing the performance of the standard Qwen3-1.7B.

Installation

To use the DataChef framework for generating your own data recipes, follow the installation steps from the GitHub repository:

conda create -n datachef python=3.12
conda activate datachef
pip install -e .

Citation

If you find this work helpful, please consider citing:

@article{chen2026datachef,
  title={DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning},
  author={Chen, Yicheng and Ma, Zerun and Xie, Xinchen and Li, Yining and Chen, Kai},
  journal={arXiv preprint arXiv:2602.11089},
  year={2026}
}

Downloads last month: 5

Safetensors

Model size

677k params

Tensor type

BF16

Model tree for yichengchen24/DataChef-32B

Base model

Qwen/Qwen3-32B

Finetuned

(496)

this model

Quantizations

2 models

Paper for yichengchen24/DataChef-32B

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

Paper • 2602.11089 • Published Feb 11 • 18