|
--- |
|
license: mit |
|
pipeline_tag: text-generation |
|
tags: |
|
- ocean |
|
- text-generation-inference |
|
- oceangpt |
|
language: |
|
- en |
|
datasets: |
|
- zjunlp/OceanInstruct |
|
--- |
|
|
|
<div align="center"> |
|
<img src="logo.jpg" width="300px"> |
|
|
|
**OceanGPT: A Large Language Model for Ocean Science Tasks** |
|
|
|
<p align="center"> |
|
<a href="https://github.com/zjunlp/OceanGPT">Project</a> • |
|
<a href="https://arxiv.org/abs/2310.02031">Paper</a> • |
|
<a href="https://huggingface.co/collections/zjunlp/oceangpt-664cc106358fdd9f09aa5157">Models</a> • |
|
<a href="http://oceangpt.zjukg.cn/">Web</a> • |
|
<a href="#quickstart">Quickstart</a> • |
|
<a href="#citation">Citation</a> |
|
</p> |
|
|
|
|
|
</div> |
|
|
|
OceanGPT-7b-v0.1 is based on LLaMA2 and has been trained on an English dataset in the ocean domain. |
|
|
|
|
|
## ⏩Quickstart |
|
### Download the model |
|
|
|
Download the model: [OceanGPT-7b-v0.1](https://huggingface.co/zjunlp/OceanGPT-7b-v0.1) |
|
|
|
```shell |
|
git lfs install |
|
git clone https://huggingface.co/zjunlp/OceanGPT-7b-v0.1 |
|
``` |
|
or |
|
``` |
|
huggingface-cli download --resume-download zjunlp/OceanGPT-7b-v0.1 --local-dir OceanGPT-7b-v0.1 --local-dir-use-symlinks False |
|
``` |
|
### Inference |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
import torch |
|
device = "cuda" # the device to load the model onto |
|
path = 'YOUR-MODEL-PATH' |
|
model = AutoModelForCausalLM.from_pretrained( |
|
path, |
|
torch_dtype=torch.bfloat16, |
|
device_map="auto" |
|
) |
|
tokenizer = AutoTokenizer.from_pretrained(path) |
|
|
|
prompt = "Which is the largest ocean in the world?" |
|
messages = [ |
|
{"role": "system", "content": "You are a helpful assistant."}, |
|
{"role": "user", "content": prompt} |
|
] |
|
text = tokenizer.apply_chat_template( |
|
messages, |
|
tokenize=False, |
|
add_generation_prompt=True |
|
) |
|
model_inputs = tokenizer([text], return_tensors="pt").to(device) |
|
|
|
generated_ids = model.generate( |
|
model_inputs.input_ids, |
|
max_new_tokens=512 |
|
) |
|
generated_ids = [ |
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) |
|
] |
|
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
``` |
|
|
|
## 📌Models |
|
|
|
| Model Name | HuggingFace | WiseModel | ModelScope | |
|
|-------------------|-----------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------| |
|
| OceanGPT-14B-v0.1 (based on Qwen) | <a href="https://huggingface.co/zjunlp/OceanGPT-14B-v0.1" target="_blank">14B</a> | <a href="https://wisemodel.cn/models/zjunlp/OceanGPT-14B-v0.1" target="_blank">14B</a> | <a href="https://modelscope.cn/models/ZJUNLP/OceanGPT-14B-v0.1" target="_blank">14B</a> | |
|
| OceanGPT-7B-v0.2 (based on Qwen) | <a href="https://huggingface.co/zjunlp/OceanGPT-7b-v0.2" target="_blank">7B</a> | <a href="https://wisemodel.cn/models/zjunlp/OceanGPT-7b-v0.2" target="_blank">7B</a> | <a href="https://modelscope.cn/models/ZJUNLP/OceanGPT-7b-v0.2" target="_blank">7B</a> | |
|
| OceanGPT-2B-v0.1 (based on MiniCPM) | <a href="https://huggingface.co/zjunlp/OceanGPT-2B-v0.1" target="_blank">2B</a> | <a href="https://wisemodel.cn/models/zjunlp/OceanGPT-2b-v0.1" target="_blank">2B</a> | <a href="https://modelscope.cn/models/ZJUNLP/OceanGPT-2B-v0.1" target="_blank">2B</a> | |
|
|
|
## 🌻Acknowledgement |
|
|
|
OceanGPT is trained based on the open-sourced large language models including [Qwen](https://huggingface.co/Qwen), [MiniCPM](https://huggingface.co/collections/openbmb/minicpm-2b-65d48bf958302b9fd25b698f), [LLaMA](https://huggingface.co/meta-llama). Thanks for their great contributions! |
|
|
|
## Limitations |
|
|
|
- The model may have hallucination issues. |
|
|
|
- We did not optimize the identity and the model may generate identity information similar to that of Qwen/MiniCPM/LLaMA/GPT series models. |
|
|
|
- The model's output is influenced by prompt tokens, which may result in inconsistent results across multiple attempts. |
|
|
|
|
|
### 🚩Citation |
|
|
|
Please cite the following paper if you use OceanGPT in your work. |
|
|
|
```bibtex |
|
@article{bi2023oceangpt, |
|
title={OceanGPT: A Large Language Model for Ocean Science Tasks}, |
|
author={Bi, Zhen and Zhang, Ningyu and Xue, Yida and Ou, Yixin and Ji, Daxiong and Zheng, Guozhou and Chen, Huajun}, |
|
journal={arXiv preprint arXiv:2310.02031}, |
|
year={2023} |
|
} |
|
|
|
``` |
