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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ECNU-SEA/SEA-S")
model = AutoModelForCausalLM.from_pretrained("ECNU-SEA/SEA-S", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ECNU-SEA/SEA-S"
# 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-S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use ECNU-SEA/SEA-S 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-S" \
    --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-S",
		"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-S" \
        --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-S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ECNU-SEA/SEA-S with Docker Model Runner:
```
docker model run hf.co/ECNU-SEA/SEA-S
```

heroding77 commited on Jul 23, 2024

Commit

604768b

verified ·

1 Parent(s): 6fbd796

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ Project Page: https://ecnu-sea.github.io/
 - 🔥🔥🔥 We have made SEA series models (7B) public !
 ## Model Description
-**_This is the SEA-S model for content standardization, and the review model SEA-E can be found [here](https://huggingface.co/ECNU-SEA/SEA-E)._**
 The SEA-S model aims to integrate all reviews for each paper into one to eliminate redundancy and errors, focusing on the major advantages and disadvantages of the paper. Specifically, we first utilize GPT-4 to integrate multiple reviews of a paper into one (From [ECNU-SEA/SEA_data](https://huggingface.co/datasets/ECNU-SEA/SEA_data)) that is in a unified format and criterion with constructive contents, and form an instruction dataset for SFT. After that, we fine-tune [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) to distill the knowledge of GPT-4. Therefore, SEA-S provides a novel paradigm for integrating peer review data in an unified format across various conferences.

 - 🔥🔥🔥 We have made SEA series models (7B) public !
 ## Model Description
+⚠️ **_This is the SEA-S model for content standardization, and the review model SEA-E can be found [here](https://huggingface.co/ECNU-SEA/SEA-E)._**
 The SEA-S model aims to integrate all reviews for each paper into one to eliminate redundancy and errors, focusing on the major advantages and disadvantages of the paper. Specifically, we first utilize GPT-4 to integrate multiple reviews of a paper into one (From [ECNU-SEA/SEA_data](https://huggingface.co/datasets/ECNU-SEA/SEA_data)) that is in a unified format and criterion with constructive contents, and form an instruction dataset for SFT. After that, we fine-tune [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) to distill the knowledge of GPT-4. Therefore, SEA-S provides a novel paradigm for integrating peer review data in an unified format across various conferences.