Image-to-Text
Transformers
Safetensors
dots_ocr
text-generation
ocr
document-parse
layout
table
formula
quantized
4-bit precision
custom_code
bitsandbytes
Instructions to use helizac/dots.ocr-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use helizac/dots.ocr-4bit 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="helizac/dots.ocr-4bit", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("helizac/dots.ocr-4bit", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,10 +14,6 @@ tags:
|
|
| 14 |
base_model: rednote-hilab/dots.ocr
|
| 15 |
---
|
| 16 |
|
| 17 |
-
<div align="center">
|
| 18 |
-
<img src="https://raw.githubusercontent.com/rednote-hilab/dots.ocr/master/assets/logo.png" width="300"/>
|
| 19 |
-
</div>
|
| 20 |
-
|
| 21 |
# dots.ocr-4bit: A 4-bit Quantized Version
|
| 22 |
|
| 23 |
This repository contains a 4-bit quantized version of the powerful `dots.ocr` model by the **Rednote HiLab**. The quantization was performed using `bitsandbytes` (NF4 precision), providing significant memory and speed improvements with minimal performance loss, making this state-of-the-art model accessible on consumer-grade GPUs.
|
|
|
|
| 14 |
base_model: rednote-hilab/dots.ocr
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
# dots.ocr-4bit: A 4-bit Quantized Version
|
| 18 |
|
| 19 |
This repository contains a 4-bit quantized version of the powerful `dots.ocr` model by the **Rednote HiLab**. The quantization was performed using `bitsandbytes` (NF4 precision), providing significant memory and speed improvements with minimal performance loss, making this state-of-the-art model accessible on consumer-grade GPUs.
|