Visual Question Answering
Transformers
ONNX
Safetensors
PyTorch
PEFT
English
tinydoc_vlm
text-generation
document-understanding
ocr
vqa
vision-language-model
tinyml
siglip
lora
open-source
huggingface
multimodal
document-ai
deep-learning
form-understanding
table-extraction
receipt-ocr
invoice-processing
smollm
fine-tuning
edge-deployment
cpu-inference
low-resource
apache-2-0
small-language-model
slm
document-processing
text-recognition
structured-extraction
retired-checkpoint
Instructions to use eulogik/TinyDoc-VLM-256M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eulogik/TinyDoc-VLM-256M with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="eulogik/TinyDoc-VLM-256M")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("eulogik/TinyDoc-VLM-256M", device_map="auto") - PEFT
How to use eulogik/TinyDoc-VLM-256M with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download chat_template.jinja from eulogik/TinyDoc-VLM-256M: direct link, hf CLI and curl.
- Browser
- Download file 368 Bytes
-
https://huggingface.co/eulogik/TinyDoc-VLM-256M/resolve/main/chat_template.jinja
- Command line
-
hf download hf://eulogik/TinyDoc-VLM-256M/chat_template.jinja
-
curl -L -o chat_template.jinja https://huggingface.co/eulogik/TinyDoc-VLM-256M/resolve/main/chat_template.jinja
368 Bytes
| {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system | |
| You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|> | |
| ' }}{% endif %}{{'<|im_start|>' + message['role'] + ' | |
| ' + message['content'] + '<|im_end|>' + ' | |
| '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant | |
| ' }}{% endif %} |