Table of Contents
Model Summary
OctoGeeX is an instruction tuned model with 6B parameters created by fine-tuning CodeGeeX2 on CommitPackFT & OASST as described in the OctoPack paper.
- Repository: bigcode-project/octopack
- Paper: OctoPack: Instruction Tuning Code Large Language Models
- Languages: 100+ Programming languages
- OctoPack🐙🎒:
Use
Intended use
The model follows instructions provided in the input. You should always preface your input with "Question: " and finish it with "Answer:", for example: "Question: Please write a function in Python that performs bubble sort.\n\nAnswer:"
Feel free to share your generations in the Community tab!
Generation
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/octogeex"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
inputs = tokenizer.encode("Question: Please write a function in Python that performs bubble sort.\n\nAnswer:", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
Training
Model
- Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
- Steps: 250k pretraining & 30 instruction tuning
- Pretraining tokens: 1 trillion pretraining & 2M instruction tuning
- Precision: bfloat16
Hardware
- Pretraining:
- GPUs: 512 Tesla A100
- Training time: 24 days
- Instruction tuning:
- GPUs: 8 Tesla A100
- Training time: 4 hours
Software
- Orchestration: Megatron-LM/Transformers
- Neural networks: PyTorch
License
本仓库的代码依照 Apache-2.0 协议开源，模型的权重的使用则需要遵循 Model License。
The code in this repository is open-source under the MIT license. The model weights are licensed under the Model License, please apply for commercial use by filling the registration form.
Citation
@article{muennighoff2023octopack,
title={OctoPack: Instruction Tuning Code Large Language Models},
author={Niklas Muennighoff and Qian Liu and Armel Zebaze and Qinkai Zheng and Binyuan Hui and Terry Yue Zhuo and Swayam Singh and Xiangru Tang and Leandro von Werra and Shayne Longpre},
journal={arXiv preprint arXiv:2308.07124},
year={2023}
}