Instructions to use ECNU-SEA/SEA-E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ECNU-SEA/SEA-E with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ECNU-SEA/SEA-E")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ECNU-SEA/SEA-E")
model = AutoModelForCausalLM.from_pretrained("ECNU-SEA/SEA-E")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ECNU-SEA/SEA-E with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ECNU-SEA/SEA-E"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ECNU-SEA/SEA-E",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ECNU-SEA/SEA-E

SGLang

How to use ECNU-SEA/SEA-E with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ECNU-SEA/SEA-E" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ECNU-SEA/SEA-E",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ECNU-SEA/SEA-E" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ECNU-SEA/SEA-E",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ECNU-SEA/SEA-E with Docker Model Runner:
```
docker model run hf.co/ECNU-SEA/SEA-E
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis

Paper Link: https://arxiv.org/abs/2407.12857

Project Page: https://ecnu-sea.github.io/

🔥 News

🔥🔥🔥 SEA is accepted by EMNLP 2024 !
🔥🔥🔥 We have made SEA series models (7B) public !

Model Description

The SEA-E model utilizes Mistral-7B-Instruct-v0.2 as its backbone. It is derived by performing supervised fine-tuning (SFT) on a high-quality peer review instruction dataset, standardized through the SEA-S model. This model can provide comprehensive and insightful review feedback for submitted papers!

Review Paper With SEA-E

from transformers import AutoModelForCausalLM, AutoTokenizer

instruction = system_prompt_dict['instruction_e']
paper = read_txt_file(mmd_file_path)
idx = paper.find("## References")
paper = paper[:idx].strip()

model_name = "/root/sea/"
tokenizer = AutoTokenizer.from_pretrained(model_name)
chat_model = AutoModelForCausalLM.from_pretrained(model_name)
chat_model.to("cuda:0")

messages = [
    {"role": "system", "content": instruction},
    {"role": "user", "content": paper},
]

encodes = tokenizer.apply_chat_template(messages, return_tensors="pt")
encodes = encodes.to("cuda:0")
len_input = encodes.shape[1]
generated_ids = chat_model.generate(encodes,max_new_tokens=8192,do_sample=True)
# response = chat_model.chat(messages)[0].response_text
response = tokenizer.batch_decode(generated_ids[: , len_input:])[0]

The code provided above is an example. For detailed usage instructions, please refer to https://github.com/ecnu-sea/sea.

Additional Clauses

The additional clauses for this project are as follows:

Commercial use is not allowed.
The SEA-E model is intended solely to provide informative reviews for authors to polish their papers instead of directly recommending acceptance/rejection on papers.
Currently, the SEA-E model is only applicable within the field of machine learning and does not guarantee insightful comments for other disciplines.

Citation

If you find our paper or models helpful, please consider cite as follows:

@inproceedings{yu2024automated,
  title={Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis},
  author={Yu, Jianxiang and Ding, Zichen and Tan, Jiaqi and Luo, Kangyang and Weng, Zhenmin and Gong, Chenghua and Zeng, Long and Cui, RenJing and Han, Chengcheng and Sun, Qiushi and others},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2024},
  pages={10164--10184},
  year={2024}
}

Downloads last month: 65

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for ECNU-SEA/SEA-E

Quantizations

2 models

Paper for ECNU-SEA/SEA-E

Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis

Paper • 2407.12857 • Published Jul 9, 2024 • 2