Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
conversational
Eval Results
text-generation-inference
Instructions to use numind/NuExtract-2.0-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use numind/NuExtract-2.0-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="numind/NuExtract-2.0-8B") 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, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("numind/NuExtract-2.0-8B") model = AutoModelForMultimodalLM.from_pretrained("numind/NuExtract-2.0-8B", device_map="auto") 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 Settings
- vLLM
How to use numind/NuExtract-2.0-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "numind/NuExtract-2.0-8B" # 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-2.0-8B", "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/NuExtract-2.0-8B
- SGLang
How to use numind/NuExtract-2.0-8B 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-2.0-8B" \ --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-2.0-8B", "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/NuExtract-2.0-8B" \ --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-2.0-8B", "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/NuExtract-2.0-8B with Docker Model Runner:
docker model run hf.co/numind/NuExtract-2.0-8B
Update chat_template.json
Browse files- chat_template.json +1 -1
chat_template.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"chat_template": "{% set
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"chat_template": "{% set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' %}\n{% for message in messages %}\n {#--- Handle User Messages with Template and Examples ---#}\n {%- if message['role'] == 'user' and template -%}\n {{- '<|im_start|>' + message['role'] -}}\n \n {#--- Template Section ---#}\n {{ '\n# Template:' }}\n {{- '\n' + template + '\n' }}\n \n {#--- Examples Section (if provided) ---#}\n {% if examples -%}\n {{- '# Examples:' }}\n {% for example in examples %}\n {{- '## Input:\n' }}\n {#--- Handle image examples ---#}\n {% if example['input'] is mapping and example['input']['type'] == 'image' %}\n {{- image_placeholder | trim -}}\n {% elif example['input'] == '<image>' %}\n {{- image_placeholder | trim -}}\n {% else %}\n {{- example['input'] -}}\n {% endif %}\n {{- '\n## Output:\n' ~ example['output'] }}\n {% endfor %}\n {%- endif %}\n \n {#--- Context Section: Handle various content types ---#}\n {{- '# Context:\n' }}\n {%- if message['content'] is string -%}\n {#--- Simple string content ---#}\n {{- message['content'] | trim -}}\n {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n {#--- Single image document ---#}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- List of content items (mixed text/images) ---#}\n {%- set ns = namespace(found=false) -%}\n {%- for content in message['content'] -%}\n {#--- Check for image documents ---#}\n {%- if content is mapping and content.get('type') == 'image' and not ns.found -%}\n {{- image_placeholder | trim -}}\n {%- set ns.found = true -%}\n {#--- Check for text placeholders with '<image>' ---#}\n {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns.found -%}\n {{- image_placeholder | trim -}}\n {%- set ns.found = true -%}\n {#--- Handle regular string content ---#}\n {%- elif content is string -%}\n {{- content | trim -}}\n {#--- Handle text content that's not an image placeholder ---#}\n {%- elif content is mapping and content.get('type') == 'text' and content.get('text') != '<image>' -%}\n {{- content['text'] | trim -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {{- '<|im_end|>\n'}}\n \n {#--- Handle All Other Messages (Assistant, System, etc.) ---#}\n {% else %}\n {{- '<|im_start|>' + message['role'] + '\n' }}\n \n {#--- Same content handling logic as above but without template/examples ---#}\n {%- if message['content'] is string -%}\n {{- message['content'] | trim }}\n {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n {{- image_placeholder | trim }}\n {%- else -%}\n {%- set ns = namespace(found=false) -%}\n {%- for content in message['content'] -%}\n {%- if content is string -%}\n {{- content | trim -}}\n {%- elif content is mapping and content.get('type') == 'text' -%}\n {{- content['text'] | trim -}}\n {%- elif content is mapping and content.get('type') == 'image' -%}\n {# Skip adding image placeholder - it's already in the text #}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {{- '<|im_end|>'}}\n {% endif %}\n{% endfor -%}\n{#--- Add Generation Prompt if Requested ---#}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant' }}\n{% endif -%}"
|
| 3 |
}
|