---
license: mit
datasets:
- databricks/databricks-dolly-15k
language:
- en
pipeline_tag: text-generation
---



# GPT-2-dolly

**GPT-2-dolly** is an instruction fine-tuned model based on the GPT-2 transformer architecture.


### Benchmark Metrics

| Metric                | GPT-2-dolly | GPT-2 (base) |
|-----------------------|-------|-------|
| Avg.                  | 29.85 | **29.99** |
| ARC (25-shot)         | 21.76 | **21.84** |
| HellaSwag (10-shot)   | 30.77 | **31.6** |
| MMLU (5-shot)         | 24.66 | **25.86** |
| TruthfulQA (0-shot)   | **42.22** | 40.67 |



We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.

### Model Details

* **Trained by**: Luiz G A Alves
* **Model type:**  **GPT-2-dolly** is an auto-regressive language model based on the GPT-2 transformer architecture.
* **Language(s)**: English

### Prompt Template
```
### Instruction:

<prompt> (without the <>)

### Response:
```

### Training Dataset

`lgaalves/gpt2-dolly` trained using the Databricks Dolly dataset [`garage-bAInd/Open-Platypus`](https://huggingface.co./datasets/garage-bAInd/Open-Platypus).


### Training Procedure

`lgaalves/gpt2-dolly` was instruction fine-tuned using LoRA on 1 T4 GPU on Google Colab. It took about 1.5 hours to train it.  


# Intended uses, limitations & biases

You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.