---
language: en 
thumbnail: "https://i.ibb.co/HBqvBFY/mountain-xianxia-chinese-scenic-landscape-craggy-mist-action-scene-pagoda-s-2336925014-1.png"
tags:
- text generation
- pytorch
license: mit

---

## Qilin-lit-6b Description

Most updated version is V1.1.0 which is finetuned on 550 MB of webnovels found on the NovelUpdates website. (https://www.novelupdates.com/)


## Downstream Uses

This model can be used for entertainment purposes and as a creative writing assistant for fiction writers.

## Usage with Kobold AI Colab (Easiest)

https://colab.research.google.com/github/KoboldAI/KoboldAI-Client/blob/main/colab/GPU.ipynb
Replace the drop-down value with "rexwang8/qilin-lit-6b" and select that model. If you get a large malloc error during the tensor loading step, you are probably using the TPU version, you will need to use the GPU version.

## Usage with Kobold AI Local

Load at AI/load a model from it's directory. Model name is "rexwang8/qilin-lit-6b". If you get a config.json not found error, reload the program and give it some time to find your GPUs.

## Example Code

```
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained('rexwang8/qilin-lit-6b')
tokenizer = AutoTokenizer.from_pretrained('rexwang8/lit-6b')

prompt = '''I had eyes but couldn't see Mount Tai!'''

input_ids = tokenizer.encode(prompt, return_tensors='pt')
output = model.generate(input_ids, do_sample=True, temperature=1.0, top_p=0.9, repetition_penalty=1.2, max_length=len(input_ids[0])+100, pad_token_id=tokenizer.eos_token_id)

generated_text = tokenizer.decode(output[0])
print(generated_text)
```

---
## Qilin-lit-6b (V1.1.0) 

Fine-tuned version of EleutherAI/gpt-j-6B (https://huggingface.co/EleutherAI/gpt-j-6B) on Coreweave's infrastructure (<https://www.coreweave.com/>) using an A40 over ~80 hours.

3150 steps, 1 epoch trained on 550 MB of primarily Xianxia genre Webnovels. (Translated to English)

---

## Team members and Acknowledgements

Rex Wang - Author

Coreweave - Computational materials

With help from:

Wes Brown, Anthony Mercurio

---

## Version History

1.1.0 - 550 MB Dataset 3150 steps (no reordering, no sampling)

1.0.0 - 100 MB Dataset 300 steps (no reordering, no sampling)