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
Eval Results
Instructions to use numind/NuExtract3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use numind/NuExtract3 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") 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/NuExtract3") model = AutoModelForMultimodalLM.from_pretrained("numind/NuExtract3") 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 olmOCR-bench old_scans result (community)
#3
by davanstrien HF Staff - opened
.eval_results/olmocrbench.yaml
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: allenai/olmOCR-bench
|
| 3 |
+
task_id: old_scans
|
| 4 |
+
value: 37.8
|
| 5 |
+
date: "2026-06-27"
|
| 6 |
+
source:
|
| 7 |
+
url: https://github.com/davanstrien/ocr-bench/blob/99f7550c/experiments/olmocr-bench-oldscans/BENCHMARKING.md
|
| 8 |
+
name: ocr-bench — old_scans multi-model comparison
|
| 9 |
+
user: davanstrien
|
| 10 |
+
notes: "old_scans.jsonl sub-score (present/absent/order); markdown mode, non-thinking, greedy, 170 DPI. NuExtract3 leads the field on present (41.6) — see source for the full sub-score breakdown."
|