---
pipeline_tag: text-generation
library_name: transformers
license: apache-2.0
tags:
  - interpretable
  - text-classification
  - text-generation
---

# Concept Bottleneck Large Language Models

This repository contains the Concept Bottleneck Large Language Model (CB-LLM) presented in [Concept Bottleneck Large Language Models](https://huggingface.co/papers/2412.07992).

[Project Website](https://lilywenglab.github.io/CB-LLMs/)

Code: [https://github.com/Trustworthy-ML-Lab/CB-LLMs](https://github.com/Trustworthy-ML-Lab/CB-LLMs)

This model offers inherent interpretability and controllability in text generation. See the linked paper and GitHub repository for details on training and usage.

## Usage (Example - Text Generation)

```python
from transformers import pipeline, AutoTokenizer

model_name = "cesun/cbllm-generation" #replace with actual model name
pipe = pipeline(
    "text-generation",
    model_name,
    tokenizer=AutoTokenizer.from_pretrained(model_name, trust_remote_code=True),
    device_map="auto",
    trust_remote_code=True,
)
print(pipe("The key to life is", max_new_tokens=20, do_sample=True)[0]["generated_text"])
```