Image-to-Text
Transformers
Safetensors
qwen3_5
image-text-to-text
vision-language
vlm
document-understanding
structured-extraction
information-extraction
ocr
document-to-markdown
markdown
rag
reasoning
multilingual
conversational
compressed-tensors
Instructions to use numind/NuExtract3-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use numind/NuExtract3-FP8 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="numind/NuExtract3-FP8") 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-FP8") model = AutoModelForImageTextToText.from_pretrained("numind/NuExtract3-FP8") 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
| { | |
| "add_prefix_space": false, | |
| "audio_bos_token": "<|audio_start|>", | |
| "audio_eos_token": "<|audio_end|>", | |
| "audio_token": "<|audio_pad|>", | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "image_token": "<|image_pad|>", | |
| "is_local": false, | |
| "local_files_only": false, | |
| "model_max_length": 262144, | |
| "model_specific_special_tokens": { | |
| "audio_bos_token": "<|audio_start|>", | |
| "audio_eos_token": "<|audio_end|>", | |
| "audio_token": "<|audio_pad|>", | |
| "image_token": "<|image_pad|>", | |
| "video_token": "<|video_pad|>", | |
| "vision_bos_token": "<|vision_start|>", | |
| "vision_eos_token": "<|vision_end|>" | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", | |
| "processor_class": "Qwen3VLProcessor", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": null, | |
| "video_token": "<|video_pad|>", | |
| "vision_bos_token": "<|vision_start|>", | |
| "vision_eos_token": "<|vision_end|>" | |
| } | |