---
language:
- en
- zh
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
---

# BlockFFN-Medium

This is the original 0.5B BlockFFN checkpoint used in the paper *BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity* for acceleration tests.

Links: [[Paper](https://arxiv.org/pdf/2507.08771)] [[Codes](https://github.com/thunlp/BlockFFN)]

## Usage

You can load and use this model simply by using `AutoTokenizer` and `AutoModelForCausalLM` from the `transformers` library.

```python
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
import torch

# Assuming the model ID is "SparseLLM/BlockFFN-Medium"
model_id = "SparseLLM/BlockFFN-Medium" 

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, trust_remote_code=True)

# Create a text generation pipeline
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# Example usage
prompt = "The quick brown fox jumps over the lazy"
result = pipe(prompt, max_new_tokens=50, do_sample=True, top_p=0.9, temperature=0.7)
print(result[0]["generated_text"])
```

## Citation

If you find our work useful for your research, please kindly cite our paper as follows:

```
@article{song2025blockffn,
      title={{BlockFFN}: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity}, 
      author={Chenyang Song and Weilin Zhao and Xu Han and Chaojun Xiao and Yingfa Chen and Yuxuan Li and Zhiyuan Liu and Maosong Sun},
      journal={arXiv preprint arXiv:2507.08771},
      year={2025},
      url={https://arxiv.org/pdf/2507.08771}, 
}
```