Instructions to use numind/NuExtract with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use numind/NuExtract with Transformers:

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

pipe = pipeline("text-generation", model="numind/NuExtract", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("numind/NuExtract", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("numind/NuExtract", trust_remote_code=True)
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use numind/NuExtract with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/numind/NuExtract

SGLang

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

Docker Model Runner
How to use numind/NuExtract with Docker Model Runner:
```
docker model run hf.co/numind/NuExtract
```

Schema format

by baconnier - opened Jun 29, 2024

Discussion

baconnier

Jun 29, 2024

•

edited Jun 29, 2024

I have some doubt on schema description.
Let’s suppose i want to extract a complex entity.
like all negative percentage number (just an example)
Do i have to put description on schema json key, or can i use key’s value ?
hope it’s in value to keep smart key name, but i have a doubt…
You should provide a more complex example in your model card .
Thanks for sharing it .

liamcripwell

Jun 29, 2024

Hi, thanks for trying out the model :)

We have tried to keep the schema/template format as simple as possible, so no descriptions are required. Generally a well-named key should be enough (e.g. {"negative_percentages": []}) for the model to work effectively. In particularly complex cases providing examples of your desired output will help.

Check out the blog post for more example/details of the schema format: https://www.numind.ai/blog/nuextract-a-foundation-model-for-structured-extraction
Also, if you want to quickly test out different approaches, you can try the model in the space: https://huggingface.co/spaces/numind/NuExtract

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment