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
```

<|input|> Were these used as special tokens during training <|output|>

#15

by aschroeder91 - opened Nov 30, 2024

Discussion

aschroeder91

Nov 30, 2024

the <|input|> and <|output|> used in inference in the model code suggests that this was used during training the model, but looking at the tokenizer config files it looks like these are not special tokens but I am not 100% sure if this was true during training.
Should I add them as special tokens during fine-tuning this model? or leave it as is?

liamcripwell

Dec 2, 2024

Hi, you can just leave them as is, they are not considered special tokens.
I also encourage you to use the newer model NuExtract-1.5, unless there is a specific reason you prefer this one.

aschroeder91

Dec 3, 2024

oh no! i meant to put this on NuExtract-1.5 (which I am using)

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