README.md

---
base_model: meta-llama/CodeLlama-7b-Instruct-hf
library_name: transformers
model_name: CodeLlama-Instruct-Python-7b
tags:
- generated_from_trainer
- trl
- sft
- CodeLlama
- Python
licence: license
datasets:
- cardiffnlp/databench
---

# Model Card for CodeLlama-Instruct-Python-7b

This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf).
Finetuned on DataBench [cardiffnlp/databench](https://huggingface.co/datasets/cardiffnlp/databench), which is publicly available on Hugging Face. 
It is specifically designed to generate a single line of Python code in response to questions from the dataset. 
The finetuning process ensures it follows instructions for producing the required Python code accurately.
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

```python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="basharatwali/CodeLlama-Instruct-Python-7b", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

 


This model was trained with SFT.

### Framework versions

- TRL: 0.13.0
- Transformers: 4.48.0.dev0
- Pytorch: 2.5.1+cu121
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## Citations



Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```