---
license: llama2
model_type: llama
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-2
  - Storywriter
---

![GOAT-70B-Storytelling](https://assets.adapt.ws/files/20231117_ehznrqludevtapck.png)
# GOAT-70B-Storytelling model

GOAT-70B-Storytelling model trained by GOAT.AI lab as a core model for autonomous story-writing agent. 


# GOAT-Storytelling-Agent
The GOAT-70B-Storytelling model has been developed as an integral component within the GOAT-Storytelling-Agent. This agent facilitates the generation of high-quality, cohesive, and captivating narratives, including stories and books. It achieves this by utilizing inputs such as plot outlines, character profiles, their interrelationships, and other relevant details. Example is provided below.

# Model description
 - **Base Architecture:** LLaMA 2 70B 
 - **License:** llama2
 - **Context window length:** 4096 tokens

### Training details

For training, we apply the standard recipe with learning rate 1e-5, batch size per GPU 6, optimizer AdamW without weight decay and we train the model via ZeRO-3 on 64xH100 GPU cluster 

### Learn more

- **Blogpost:** [GOAT-Storytelling: Arbitrarily Long Story Writing Agent](https://www.blog.goat.ai/goat-st/)
- **GitHub:** [here](https://github.com/GOAT-AI-lab/GOAT-Storytelling-Agent)
- **Generated examples:** [here](https://huggingface.co/datasets/GOAT-AI/generated-novels)
## Uses

The main purpose of GOAT-70B-Storytelling is to generate books, novels, movie scripts and etc. as an agent in coping with our GOAT-Storytelling-Agent. It is specifically designed for storywriters.

## Usage


Usage can be either self-hosted via `transformers` or used with Spaces

```python
import torch

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "GOAT-AI/GOAT-70B-Storytelling"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16
)
```
Currently, we support LLM endpoint generation, where you need to send a post request to the generation endpoint (we recommend using Text Generation Inference by HuggingFace)

First, modify config.py and add your generation endpoint.

Then you can use it inside via GOAT-Storytelling-Agent:

```python
from goat_storytelling_agent.story_processor.prompt_manager import generate_story

novel_scenes = generate_story('never too much coffee', form='novel')
```
## License

GOAT-70B-Storytelling model is based on [Meta's LLaMA-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf), and using own datasets.  

GOAT-70B-Storytelling model weights are available under LLAMA-2 license.
### Risks and Biases 

GOAT-70B-Storytelling model can produce factually incorrect output and should not be relied on to deliver factually accurate information. Therefore, the GOAT-70B-Storytelling model could possibly generate wrong, biased, or otherwise offensive outputs.