---
library_name: transformers
license: apache-2.0
datasets:
- UKPLab/dara
---

# DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs

## Model Information
<!-- Provide a quick summary of what the model is/does. -->
This model is a fine-tuned semantic parsing LLM agent for KGQA.
We fine-tune the llama-2-7B on our curated reasoning trajectory https://huggingface.co/datasets/UKPLab/dara.


## Model Usage
```python
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
                "UKPLab/dara-llama-2-7b",
                torch_dtype=torch.float16,
                device_map="auto",
                cache_dir = "cache"
            )
```
For more information, please check the repository https://github.com/UKPLab/acl2024-DARA

## Hyperparameters
- Learning rate: 2e-5
- Batch size: 4
- Training epochs: 10