README.md

---
language:
- en
- zh
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- moe
- llm
- acceleration
---

# BlockFFN-Large

This is the original 0.8B 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)]

### How to use

You can load and use this model directly with the `transformers` library. Ensure you set `trust_remote_code=True` due to the custom architecture.

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

model_name = "SparseLLM/BlockFFN-Large"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
model.eval() # Set model to evaluation mode

text = "The quick brown fox jumps over the lazy"
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate text
outputs = model.generate(**inputs, max_new_tokens=20, do_sample=True, temperature=0.8, top_p=0.8)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(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}, 
}