qilin-lit-6b / README.md
rexwang8's picture
Update README.md
e3769ce
|
raw
history blame
2.18 kB
metadata
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

Open the code that loads the models and replace a path with "rexwang8/qilin-lit-6b" and select that model. If you get a large malloc error during the tensor loading step, this will be resolved in the next major 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)

ps. lit stands for literature, not related to Anthony's Lit model


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 epoch 1

1.0.0 - 100 MB Dataset 300 steps epoch 1