Sponsored by
YouArt
zjunlp / OceanGPT-basic-4B-Thinking
Model's Last Updated: December 29 2025
text-generation
Introduction of OceanGPT-basic-4B-Thinking
Model Details of OceanGPT-basic-4B-Thinking
OceanGPT(沧渊): A Large Language Model for Ocean Science Tasks
OceanGPT-basic is based on Qwen3 and has been trained on an English and Chinese dataset in the ocean domain ( recent update 20251223 ) .
Please note that the models and data in this repository are updated regularly to fix errors. The latest update date will be added to the README for your reference.
- ❗ We will continue to update.
- ❗ Disclaimer: This project is purely an academic exploration rather than a product. Please be aware that due to the inherent limitations of large language models, there may be issues such as hallucinations.
⏩Quickstart
Download the model
Download the model: zjunlp/OceanGPT-basic-4B-Thinking
git lfs install
git clone https://huggingface.co/zjunlp/OceanGPT-basic-4B-Thinking
or
huggingface-cli download --resume-download zjunlp/OceanGPT-basic-4B-Thinking --local-dir OceanGPT-basic-4B-Thinking --local-dir-use-symlinks False
Inference
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "zjunlp/OceanGPT-basic-4B-Thinking"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
system_prompt = "你是海洋知识专家，负责解答各类海洋相关问题(You are a marine knowledge expert, responsible for answering all marine-related questions)."
question = "<Your Question>"
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": question}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=4096
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content) # no opening <think> tag
print("content:", content)
🌻Acknowledgement
OceanGPT (沧渊) is trained based on the open-sourced large language models including Qwen , MiniCPM , LLaMA .
OceanGPT is trained based on the open-sourced data and tools including Moos , UATD , Forward-looking Sonar Detection Dataset , NKSID , SeabedObjects-KLSG , Marine Debris .
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}
}
Runs of zjunlp OceanGPT-basic-4B-Thinking on huggingface.co
107
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
96
30-day runs
More Information About OceanGPT-basic-4B-Thinking huggingface.co Model
Url of OceanGPT-basic-4B-Thinking
OceanGPT-basic-4B-Thinking huggingface.co Url
Provider of OceanGPT-basic-4B-Thinking huggingface.co
Other API from zjunlp
Total runs:
214
Run Growth:
174
Growth Rate:
81.31%
Total runs:
125
Run Growth:
-86
Growth Rate:
-68.80%
Total runs:
84
Run Growth:
80
Growth Rate:
95.24%
Total runs:
58
Run Growth:
51
Growth Rate:
87.93%
Total runs:
45
Run Growth:
41
Growth Rate:
91.11%
Total runs:
38
Run Growth:
38
Growth Rate:
100.00%
Total runs:
33
Run Growth:
-6
Growth Rate:
-18.18%
Total runs:
30
Run Growth:
22
Growth Rate:
75.86%
Total runs:
17
Run Growth:
2
Growth Rate:
11.76%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
11
Run Growth:
11
Growth Rate:
100.00%
Total runs:
9
Run Growth:
7
Growth Rate:
77.78%
Total runs:
6
Run Growth:
-4
Growth Rate:
-66.67%
Total runs:
6
Run Growth:
-3
Growth Rate:
-75.00%
Total runs:
4
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
-8
Growth Rate:
-266.67%
Total runs:
4
Run Growth:
-5
Growth Rate:
-166.67%
Total runs:
4
Run Growth:
-5
Growth Rate:
-125.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
1
Growth Rate:
50.00%
Total runs:
2
Run Growth:
-7
Growth Rate:
-700.00%
Total runs:
1
Run Growth:
-2
Growth Rate:
-200.00%
Total runs:
1
Run Growth:
-1
Growth Rate:
-100.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%