OceanGPT

OceanGPT copied to clipboard

OceanGPT (沧渊): A Large Language Model for Ocean Science Tasks

Project • Paper • Models • Web • Overview • Quickstart • Citation

Table of Contents

• What's New
• Overview
• Quickstart
• Models
• Citation

🔔News

• 2024-07-04, we release OceanGPT-14B/2B-v0.1 and OceanGPT-7B-v0.2 based on Qwen and MiniCPM.
• 2024-06-04, OceanGPT is accepted by ACL 2024. 🎉🎉
• 2023-10-04, we release the paper "OceanGPT: A Large Language Model for Ocean Science Tasks" and release OceanGPT-7B-v0.1 based on LLaMA2.
• 2023-05-01, we launch the OceanGPT (沧渊) project.

🌟Overview

This is the OceanGPT (沧渊) project, which aims to build LLMs for ocean science tasks.

• ❗Disclaimer: This project is purely an academic exploration rather than a product(本项目仅为学术探索并非产品应用). Please be aware that due to the inherent limitations of large language models, there may be issues such as hallucinations.

⏩Quickstart

conda create -n py3.11 python=3.11
conda activate py3.11
pip install -r requirements.txt

Download the model

Download from HuggingFace

git lfs install
git clone https://huggingface.co/zjunlp/OceanGPT-14B-v0.1

or

huggingface-cli download --resume-download zjunlp/OceanGPT-14B-v0.1 --local-dir OceanGPT-14B-v0.1 --local-dir-use-symlinks False

Download from WiseModel

git lfs install
git clone https://www.wisemodel.cn/zjunlp/OceanGPT-14B-v0.1.git

Download from ModelScope

git lfs install
git clone https://www.modelscope.cn/ZJUNLP/OceanGPT-14B-v0.1.git

Inference

Inference by HuggingFace

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]

Inference by vllm

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

path = 'YOUR-MODEL-PATH'

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
)

sampling_params = SamplingParams(temperature=0.8, top_k=50)
llm = LLM(model=path)

response = llm.generate(text, sampling_params)

📌Models

🌻Acknowledgement

OceanGPT (沧渊) is trained based on the open-sourced large language models including Qwen, MiniCPM, 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.

• The model requires the inclusion of specific simulator code instructions for training in order to possess simulated embodied intelligence capabilities (the simulator is subject to copyright restrictions and cannot be made available for now), and its current capabilities are quite limited.

🚩Citation

Please cite the following paper if you use OceanGPT in your work.

@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}
}