You can deploy this model and start earning money today!

numind/
NuExtract-2-4B-experimental

Name: NuExtract-2-4B-experimental
Availability: InStock

OpenGVLab/InternVL2_5-4B

finetune

mit

Views

No views yet

NuExtract-2-4B [experimental version] by NuMind 🔥

NuExtract 2.0 experimental is a family of models trained specifically for structured information extraction tasks. It supports both multimodal inputs and is multilingual. NB: This is an experimental version that will be superseeded by NuExtract 2.0

We provide several versions of different sizes, all based on the InternVL2.5 family.

Model Size	Model Name	Base Model	Huggingface Link
2B	NuExtract-2.0-2B	InternVL2_5-2B	NuExtract-2-2B
4B	NuExtract-2.0-4B	InternVL2_5-4B	NuExtract-2-4B
8B	NuExtract-2.0-8B	InternVL2_5-8B	NuExtract-2-8B

Overview

To use the model, provide an input text/image and a JSON template describing the information you need to extract. The template should be a JSON object, specifying field names and their expected type.

Support types include:

verbatim-string - instructs the model to extract text that is present verbatim in the input.
string - a generic string field that can incorporate paraphrasing/abstraction.
integer - a whole number.
number - a whole or decimal number.
date-time - ISO formatted date.
Array of any of the above types (e.g. ["string"])
enum - a choice from set of possible answers (represented in template as an array of options, e.g. ["yes", "no", "maybe"]).
multi-label - an enum that can have multiple possible answers (represented in template as a double-wrapped array, e.g. [["A", "B", "C"]]).

If the model does not identify relevant information for a field, it will return null or [] (for arrays and multi-labels).

The following is an example template:

json

{
  "first_name": "verbatim-string",
  "last_name": "verbatim-string",
  "description": "string",
  "age": "integer",
  "gpa": "number",
  "birth_date": "date-time",
  "nationality": ["France", "England", "Japan", "USA", "China"],
  "languages_spoken": [["English", "French", "Japanese", "Mandarin", "Spanish"]]
}

An example output:

json

{
  "first_name": "Susan",
  "last_name": "Smith",
  "description": "A student studying computer science.",
  "age": 20,
  "gpa": 3.7,
  "birth_date": "2005-03-01",
  "nationality": "England",
  "languages_spoken": ["English", "French"]
}

⚠️ We recommend using NuExtract with a temperature at or very close to 0. Some inference frameworks, such as Ollama, use a default of 0.7 which is not well suited to many extraction tasks.

Inference

Use the following code to handle loading and preprocessing of input data:

python

import torch
import torchvision.transforms as T
from PIL import Image
from torchvision.transforms.functional import InterpolationMode

IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform

def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio

def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # calculate the existing image aspect ratio
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # find the closest aspect ratio to the target
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # calculate the target width and height
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # resize the image
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        # split the image
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images

def load_image(image_file, input_size=448, max_num=12):
    image = Image.open(image_file).convert('RGB')
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values

def prepare_inputs(messages, image_paths, tokenizer, device='cuda', dtype=torch.bfloat16):
    """
    Prepares multi-modal input components (supports multiple images per prompt).
    
    Args:
        messages: List of input messages/prompts (strings or dicts with 'role' and 'content')
        image_paths: List where each element is either None (for text-only) or a list of image paths
        tokenizer: The tokenizer to use for applying chat templates
        device: Device to place tensors on ('cuda', 'cpu', etc.)
        dtype: Data type for image tensors (default: torch.bfloat16)
    
    Returns:
        dict: Contains 'prompts', 'pixel_values_list', and 'num_patches_list' ready for the model
    """
    # Make sure image_paths list is at least as long as messages
    if len(image_paths) < len(messages):
        # Pad with None for text-only messages
        image_paths = image_paths + [None] * (len(messages) - len(image_paths))
    
    # Process images and collect patch information
    loaded_images = []
    num_patches_list = []
    for paths in image_paths:
        if paths and isinstance(paths, list) and len(paths) > 0:
            # Load each image in this prompt
            prompt_images = []
            prompt_patches = []
            
            for path in paths:
                # Load the image
                img = load_image(path).to(dtype=dtype, device=device)
                
                # Ensure img has correct shape [patches, C, H, W]
                if len(img.shape) == 3:  # [C, H, W] -> [1, C, H, W]
                    img = img.unsqueeze(0)
                    
                prompt_images.append(img)
                # Record the number of patches for this image
                prompt_patches.append(img.shape[0])
            
            loaded_images.append(prompt_images)
            num_patches_list.append(prompt_patches)
        else:
            # Text-only prompt
            loaded_images.append(None)
            num_patches_list.append([])
    
    # Create the concatenated pixel_values_list
    pixel_values_list = []
    for prompt_images in loaded_images:
        if prompt_images:
            # Concatenate all images for this prompt
            pixel_values_list.append(torch.cat(prompt_images, dim=0))
        else:
            # Text-only prompt
            pixel_values_list.append(None)
    
    # Format messages for the model
    if all(isinstance(m, str) for m in messages):
        # Simple string messages: convert to chat format
        batch_messages = [
            [{"role": "user", "content": message}] 
            for message in messages
        ]
    else:
        # Assume messages are already in the right format
        batch_messages = messages
    
    # Apply chat template
    prompts = tokenizer.apply_chat_template(
        batch_messages,
        tokenize=False,
        add_generation_prompt=True
    )
    
    return {
        'prompts': prompts,
        'pixel_values_list': pixel_values_list,
        'num_patches_list': num_patches_list
    }

def construct_message(text, template, examples=None):
    """
    Construct the individual NuExtract message texts, prior to chat template formatting.
    """
    # add few-shot examples if needed
    if examples is not None and len(examples) > 0:
        icl = "# Examples:\n"
        for row in examples:
            icl += f"## Input:\n{row['input']}\n## Output:\n{row['output']}\n"
    else:
        icl = ""
        
    return f"""# Template:\n{template}\n{icl}# Context:\n{text}"""

To handle inference:

python

IMG_START_TOKEN='<img>'
IMG_END_TOKEN='</img>'
IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'

def nuextract_generate(model, tokenizer, prompts, generation_config, pixel_values_list=None, num_patches_list=None):
    """
    Generate responses for a batch of NuExtract inputs.
    Support for multiple and varying numbers of images per prompt.
    
    Args:
        model: The vision-language model
        tokenizer: The tokenizer for the model
        pixel_values_list: List of tensor batches, one per prompt
                          Each batch has shape [num_images, channels, height, width] or None for text-only prompts
        prompts: List of text prompts
        generation_config: Configuration for text generation
        num_patches_list: List of lists, each containing patch counts for images in a prompt
        
    Returns:
        List of generated responses
    """
    img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
    model.img_context_token_id = img_context_token_id
    
    # Replace all image placeholders with appropriate tokens
    modified_prompts = []
    total_image_files = 0
    total_patches = 0
    image_containing_prompts = []
    for idx, prompt in enumerate(prompts):
        # check if this prompt has images
        has_images = (pixel_values_list and
                      idx < len(pixel_values_list) and 
                      pixel_values_list[idx] is not None and 
                      isinstance(pixel_values_list[idx], torch.Tensor) and
                      pixel_values_list[idx].shape[0] > 0)
        
        if has_images:
            # prompt with image placeholders
            image_containing_prompts.append(idx)
            modified_prompt = prompt
            
            patches = num_patches_list[idx] if (num_patches_list and idx < len(num_patches_list)) else []
            num_images = len(patches)
            total_image_files += num_images
            total_patches += sum(patches)
            
            # replace each <image> placeholder with image tokens
            for i, num_patches in enumerate(patches):
                image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * model.num_image_token * num_patches + IMG_END_TOKEN
                modified_prompt = modified_prompt.replace('<image>', image_tokens, 1)
        else:
            # text-only prompt
            modified_prompt = prompt
        
        modified_prompts.append(modified_prompt)
    
    # process all prompts in a single batch
    tokenizer.padding_side = 'left'
    model_inputs = tokenizer(modified_prompts, return_tensors='pt', padding=True)
    input_ids = model_inputs['input_ids'].to(model.device)
    attention_mask = model_inputs['attention_mask'].to(model.device)
    
    eos_token_id = tokenizer.convert_tokens_to_ids("<|im_end|>\n".strip())
    generation_config['eos_token_id'] = eos_token_id
    
    # prepare pixel values
    flattened_pixel_values = None
    if image_containing_prompts:
        # collect and concatenate all image tensors
        all_pixel_values = []
        for idx in image_containing_prompts:
            all_pixel_values.append(pixel_values_list[idx])
        
        flattened_pixel_values = torch.cat(all_pixel_values, dim=0)
        print(f"Processing batch with {len(prompts)} prompts, {total_image_files} actual images, and {total_patches} total patches")
    else:
        print(f"Processing text-only batch with {len(prompts)} prompts")
    
    # generate outputs
    outputs = model.generate(
        pixel_values=flattened_pixel_values,  # will be None for text-only prompts
        input_ids=input_ids,
        attention_mask=attention_mask,
        **generation_config
    )
    
    # Decode responses
    responses = tokenizer.batch_decode(outputs, skip_special_tokens=True)
    
    return responses

To load the model:

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = ""

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, padding_side='left')
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, 
                                             torch_dtype=torch.bfloat16,
                                             attn_implementation="flash_attention_2" # we recommend using flash attention
                                            ).to("cuda")

Simple 0-shot text-only example:

python

template = """{"names": ["verbatim-string"]}"""
text = "John went to the restaurant with Mary. James went to the cinema."

input_messages = [construct_message(text, template)]

input_content = prepare_inputs(
    messages=input_messages,
    image_paths=[],
    tokenizer=tokenizer,
)

generation_config = {"do_sample": False, "num_beams": 1, "max_new_tokens": 2048}

with torch.no_grad():
    result = nuextract_generate(
        model=model,
        tokenizer=tokenizer,
        prompts=input_content['prompts'],
        pixel_values_list=input_content['pixel_values_list'],
        num_patches_list=input_content['num_patches_list'],
        generation_config=generation_config
    )
for y in result:
    print(y)
# {"names": ["John", "Mary", "James"]}

Text-only input with an in-context example:

python

template = """{"names": ["verbatim-string"], "female_names": ["verbatim-string"]}"""
text = "John went to the restaurant with Mary. James went to the cinema."
examples = [
    {
        "input": "Stephen is the manager at Susan's store.",
        "output": """{"names": ["STEPHEN", "SUSAN"], "female_names": ["SUSAN"]}"""
    }
]

input_messages = [construct_message(text, template, examples)]

input_content = prepare_inputs(
    messages=input_messages,
    image_paths=[],
    tokenizer=tokenizer,
)

generation_config = {"do_sample": False, "num_beams": 1, "max_new_tokens": 2048}

with torch.no_grad():
    result = nuextract_generate(
        model=model,
        tokenizer=tokenizer,
        prompts=input_content['prompts'],
        pixel_values_list=input_content['pixel_values_list'],
        num_patches_list=input_content['num_patches_list'],
        generation_config=generation_config
    )
for y in result:
    print(y)
# {"names": ["JOHN", "MARY", "JAMES"], "female_names": ["MARY"]}

Example with image input and an in-context example. Image inputs should use <image> placeholder instead of text and image paths should be provided in a list in order of appearance in the prompt (in this example 0.jpg will be for the in-context example and 1.jpg for the true input).

python

template = """{"store": "verbatim-string"}"""
text = "<image>"
examples = [
    {
        "input": "<image>",
        "output": """{"store": "Walmart"}"""
    }
]

input_messages = [construct_message(text, template, examples)]

images = [
    ["0.jpg", "1.jpg"]
]

input_content = prepare_inputs(
    messages=input_messages,
    image_paths=images,
    tokenizer=tokenizer,
)

generation_config = {"do_sample": False, "num_beams": 1, "max_new_tokens": 2048}

with torch.no_grad():
    result = nuextract_generate(
        model=model,
        tokenizer=tokenizer,
        prompts=input_content['prompts'],
        pixel_values_list=input_content['pixel_values_list'],
        num_patches_list=input_content['num_patches_list'],
        generation_config=generation_config
    )
for y in result:
    print(y)
# {"store": "Trader Joe's"}

Multi-modal batched input:

python

inputs = [
    # image input with no ICL examples
    {
        "text": "<image>",
        "template": """{"store_name": "verbatim-string"}""",
        "examples": None,
    },
    # image input with 1 ICL example
    {
        "text": "<image>",
        "template": """{"store_name": "verbatim-string"}""",
        "examples": [
            {
                "input": "<image>",
                "output": """{"store_name": "Walmart"}""",
            }
        ],
    },
    # text input with no ICL examples
    {
        "text": "John went to the restaurant with Mary. James went to the cinema.",
        "template": """{"names": ["verbatim-string"]}""",
        "examples": None,
    },
    # text input with ICL example
    {
        "text": "John went to the restaurant with Mary. James went to the cinema.",
        "template": """{"names": ["verbatim-string"], "female_names": ["verbatim-string"]}""",
        "examples": [
            {
                "input": "Stephen is the manager at Susan's store.",
                "output": """{"names": ["STEPHEN", "SUSAN"], "female_names": ["SUSAN"]}"""
            }
        ],
    },
]

input_messages = [
    construct_message(
        x["text"], 
        x["template"], 
        x["examples"]
    ) for x in inputs
]

images = [
    ["0.jpg"],
    ["0.jpg", "1.jpg"],
    None,
    None
]

input_content = prepare_inputs(
    messages=input_messages,
    image_paths=images,
    tokenizer=tokenizer,
)

generation_config = {"do_sample": False, "num_beams": 1, "max_new_tokens": 2048}

with torch.no_grad():
    result = nuextract_generate(
        model=model,
        tokenizer=tokenizer,
        prompts=input_content['prompts'],
        pixel_values_list=input_content['pixel_values_list'],
        num_patches_list=input_content['num_patches_list'],
        generation_config=generation_config
    )
for y in result:
    print(y)
# {"store_name": "WAL*MART"}
# {"store_name": "Trader Joe's"}
# {"names": ["John", "Mary", "James"]}
# {"names": ["JOHN", "MARY", "JAMES"], "female_names": ["MARY"]}

Template Generation

If you want to convert existing schema files you have in other formats (e.g. XML, YAML, etc.) or start from an example, NuExtract 2 models can automatically generate this for you.

E.g. convert XML into a NuExtract template:

python

def generate_template(description):
    input_messages = [description]
    input_content = prepare_inputs(
        messages=input_messages,
        image_paths=[],
        tokenizer=tokenizer,
    )

    generation_config = {"do_sample": True, "temperature": 0.4, "max_new_tokens": 256}

    with torch.no_grad():
        result = nuextract_generate(
            model=model,
            tokenizer=tokenizer,
            prompts=input_content['prompts'],
            pixel_values_list=input_content['pixel_values_list'],
            num_patches_list=input_content['num_patches_list'],
            generation_config=generation_config
        )
    return result[0]

xml_template = """<SportResult>
    <Date></Date>
    <Sport></Sport>
    <Venue></Venue>
    <HomeTeam></HomeTeam>
    <AwayTeam></AwayTeam>
    <HomeScore></HomeScore>
    <AwayScore></AwayScore>
    <TopScorer></TopScorer>
</SportResult>"""
result = generate_template(xml_template)
    
print(result)
# { 
#     "SportResult": {
#         "Date": "date-time",
#         "Sport": "verbatim-string",
#         "Venue": "verbatim-string",
#         "HomeTeam": "verbatim-string",
#         "AwayTeam": "verbatim-string",
#         "HomeScore": "integer",
#         "AwayScore": "integer",
#         "TopScorer": "verbatim-string"
#     }
# }

E.g. generate a template from natural language description:

python

text = """Give me relevant info about startup companies mentioned."""
result = generate_template(text)
    
print(result)
# {
#     "Startup_Companies": [
#         {
#             "Name": "verbatim-string",
#             "Products": [
#                 "string"
#             ],
#             "Location": "verbatim-string",
#             "Company_Type": [
#                 "Technology",
#                 "Finance",
#                 "Health",
#                 "Education",
#                 "Other"
#             ]
#         }
#     ]
# }

numind/NuExtract-2-4B-experimental

NuExtract-2-4B [experimental version] by NuMind 🔥

Overview

Inference

Template Generation

numind/
NuExtract-2-4B-experimental