Instructions to use MiniLLM/MiniPLM-Qwen-500M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniLLM/MiniPLM-Qwen-500M with Transformers:

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

pipe = pipeline("text-generation", model="MiniLLM/MiniPLM-Qwen-500M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MiniLLM/MiniPLM-Qwen-500M")
model = AutoModelForCausalLM.from_pretrained("MiniLLM/MiniPLM-Qwen-500M")
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 MiniLLM/MiniPLM-Qwen-500M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniLLM/MiniPLM-Qwen-500M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniLLM/MiniPLM-Qwen-500M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniLLM/MiniPLM-Qwen-500M

SGLang

How to use MiniLLM/MiniPLM-Qwen-500M 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 "MiniLLM/MiniPLM-Qwen-500M" \
    --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": "MiniLLM/MiniPLM-Qwen-500M",
		"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 "MiniLLM/MiniPLM-Qwen-500M" \
        --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": "MiniLLM/MiniPLM-Qwen-500M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniLLM/MiniPLM-Qwen-500M with Docker Model Runner:
```
docker model run hf.co/MiniLLM/MiniPLM-Qwen-500M
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MinPLM-Qwen-500M

paper | code

MiniPLM-Qwen-500M is a 500M model with Qwen achitecture pre-trained from scratch on the Pile using the MiniPLM knowledge distillation framework with the offcial Qwen1.5-1.8B as the teacher model.

We also open-source the pre-training corpus refined by Difference Sampling in MiniPLM for reproducibility.

Paper Abstract

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces challenges in efficiency, flexibility, and effectiveness. Existing methods either incur high computational costs due to online teacher inference, require tokenization matching between teacher and student LMs, or risk losing the difficulty and diversity of the teacher-generated training data. To address these issues, we propose MiniPLM, a KD framework for pre-training LMs by refining the training data distribution with the teacher's knowledge. For efficiency, MiniPLM performs offline teacher LM inference, allowing KD for multiple student LMs without adding training-time costs. For flexibility, MiniPLM operates solely on the training corpus, enabling KD across model families. For effectiveness, MiniPLM leverages the differences between large and small LMs to enhance the difficulty and diversity of the training data, helping student LMs acquire versatile and sophisticated knowledge. Extensive experiments demonstrate that MiniPLM boosts the student LMs' performance on 9 widely used downstream tasks, improves the language modeling capabilities, and reduces pre-training computation. The benefit of MiniPLM extends to large pre-training scales, evidenced by the extrapolation of the scaling curves. Further analysis reveals that MiniPLM supports KD across model families and enhances the utilization of pre-training data. Our model, code, and data are available at https://github.com/thu-coai/MiniPLM.

Evaluation

MiniPLM models achieves better performance given the same computation and scales well across model sizes:

Baseline Models

Citation

@article{miniplm,
    title={MiniPLM: Knowledge Distillation for Pre-Training Language Models}, 
    author={Yuxian Gu and Hao Zhou and Fandong Meng and Jie Zhou and Minlie Huang},
    journal={arXiv preprint arXiv:2410.17215},
    year={2024}
}