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



# xgen-7b-8k-dolly

**xgen-7b-8k-dolly** is an instruction fine-tuned model based on the XGen-7B model pre-trained under 8K sequence length.


### Benchmark Metrics

| Metric                | xgen-7b-8k-dolly | xgen-7b-8k-base |
|-----------------------|-------|-------|
| Avg.                  | - | - |
| ARC (25-shot)         | - | - |
| HellaSwag (10-shot)   | - | - |
| MMLU (5-shot)         | - | - |
| TruthfulQA (0-shot)   | - | - |



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:**  **xgen-7b-8k-dolly** is an auto-regressive language model based on the XGen-7B model pre-trained under 8K sequence length.
* **Language(s)**: English

### How to use:

```python
# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/xgen-7b-8k-dolly")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])
```

or, you can load the model direclty using:

```python
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lgaalves/xgen-7b-8k-dolly")
model = AutoModelForCausalLM.from_pretrained("lgaalves/xgen-7b-8k-dolly")
```

### Training Dataset

`lgaalves/xgen-7b-8k-dolly` trained using the Databricks Dolly dataset [`databricks/databricks-dolly-15k`](https://huggingface.co/datasets/databricks/databricks-dolly-15k).


### Training Procedure

`lgaalves/xgen-7b-8k-dolly` was instruction fine-tuned using LoRA.


# 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.