Instructions to use MiniLLM/MiniPLM-Mamba-130M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniLLM/MiniPLM-Mamba-130M with Transformers:

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

pipe = pipeline("text-generation", model="MiniLLM/MiniPLM-Mamba-130M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MiniLLM/MiniPLM-Mamba-130M")
model = AutoModelForCausalLM.from_pretrained("MiniLLM/MiniPLM-Mamba-130M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiniLLM/MiniPLM-Mamba-130M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniLLM/MiniPLM-Mamba-130M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniLLM/MiniPLM-Mamba-130M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MiniLLM/MiniPLM-Mamba-130M

SGLang

How to use MiniLLM/MiniPLM-Mamba-130M 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-Mamba-130M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniLLM/MiniPLM-Mamba-130M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Mamba-130M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniLLM/MiniPLM-Mamba-130M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MiniLLM/MiniPLM-Mamba-130M with Docker Model Runner:
```
docker model run hf.co/MiniLLM/MiniPLM-Mamba-130M
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniPLM-Mamba-130M

paper | code

MiniPLM-Mamba-130M is a 130M parameter language model with the Mamba architecture pre-trained from scratch on the Pile using the MiniPLM knowledge distillation framework. It uses the official Qwen1.5-1.8B as the teacher model. This model demonstrates the flexibility of the MiniPLM framework in conducting knowledge distillation across model families. The pre-training corpus refined by Difference Sampling in MiniPLM is open-sourced for reproducibility.

MiniPLM: Knowledge Distillation for Pre-Training Language Models

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, MiniPLM is proposed, 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.

Evaluation

MiniPLM models achieve better performance given the same computation and scale well across model sizes:

Baseline Models

Conventional Pre-Training

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}
}