Instructions to use numind/NuExtract3-W8A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use numind/NuExtract3-W8A8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="numind/NuExtract3-W8A8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("numind/NuExtract3-W8A8")
model = AutoModelForImageTextToText.from_pretrained("numind/NuExtract3-W8A8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use numind/NuExtract3-W8A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "numind/NuExtract3-W8A8"
# 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/NuExtract3-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/numind/NuExtract3-W8A8

SGLang

How to use numind/NuExtract3-W8A8 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/NuExtract3-W8A8" \
    --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/NuExtract3-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/NuExtract3-W8A8" \
        --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/NuExtract3-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use numind/NuExtract3-W8A8 with Docker Model Runner:
```
docker model run hf.co/numind/NuExtract3-W8A8
```

SorenDreano commited on 5 days ago

Commit

5a9fee3

verified ·

1 Parent(s): b7361da

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

chat_template.jinja +4 -4

chat_template.jinja CHANGED Viewed

@@ -101,10 +101,10 @@
     {%- elif message.role == 'user' and message.name != "example" -%}
         {%- set content = render_content(message.content, true)|trim %}
         {{- content + '\n' -}}
-    {%- elif message.role == 'assistant' and not loop.last %}
-        {# llama.cpp renders a synthetic init example with an assistant turn in
-           the middle; ignore it so valid NuExtract prompts render unchanged.
-           {{- raise_exception('Assistant message must be at the end.') }} #}
     {%- endif %}
 {%- endfor -%}
 {{- '【document_end】<|im_end|>\n' -}}

     {%- elif message.role == 'user' and message.name != "example" -%}
         {%- set content = render_content(message.content, true)|trim %}
         {{- content + '\n' -}}
+    {# {%- elif message.role == 'assistant' and not loop.last %}
+        llama.cpp renders a synthetic init example with an assistant turn in
+        the middle; ignore it so valid NuExtract prompts render unchanged.
+        {{- raise_exception('Assistant message must be at the end.') }} #}
     {%- endif %}
 {%- endfor -%}
 {{- '【document_end】<|im_end|>\n' -}}