Instructions to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PaddlePaddle/PaddleOCR-VL-1.6-GGUF",
	filename="PaddleOCR-VL-1.6-GGUF-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF
# Run inference directly in the terminal:
llama-cli -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF
# Run inference directly in the terminal:
llama-cli -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF
# Run inference directly in the terminal:
./llama-cli -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PaddlePaddle/PaddleOCR-VL-1.6-GGUF

Use Docker

docker model run hf.co/PaddlePaddle/PaddleOCR-VL-1.6-GGUF

LM Studio
Jan
Ollama
How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with Ollama:
```
ollama run hf.co/PaddlePaddle/PaddleOCR-VL-1.6-GGUF
```

Unsloth Studio

How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PaddlePaddle/PaddleOCR-VL-1.6-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PaddlePaddle/PaddleOCR-VL-1.6-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PaddlePaddle/PaddleOCR-VL-1.6-GGUF to start chatting

Docker Model Runner
How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with Docker Model Runner:
```
docker model run hf.co/PaddlePaddle/PaddleOCR-VL-1.6-GGUF
```

Lemonade

How to use PaddlePaddle/PaddleOCR-VL-1.6-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PaddlePaddle/PaddleOCR-VL-1.6-GGUF

Run and chat with the model

lemonade run user.PaddleOCR-VL-1.6-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Add pipeline tag and library name to model card

by nielsr HF Staff - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

nielsr

2 days ago

This PR improves the model card by adding the image-text-to-text pipeline tag and the transformers library name to the YAML metadata. This ensures the model is correctly categorized on the Hugging Face Hub and enables the "Use in Transformers" code snippet button. I've also ensured that the research paper and GitHub repository are clearly referenced in the content.

Add pipeline tag and library name to model card4152bebc

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment