Instructions to use fridaycandour/PaddleOCR-VL-1.5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fridaycandour/PaddleOCR-VL-1.5-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fridaycandour/PaddleOCR-VL-1.5-GGUF",
	filename="PaddleOCR-VL-1.5-BF16.gguf",
)

llm.create_chat_completion(
	messages = "\"cats.jpg\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use fridaycandour/PaddleOCR-VL-1.5-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

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 fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

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 fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

Use Docker

docker model run hf.co/fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

LM Studio
Jan
Ollama
How to use fridaycandour/PaddleOCR-VL-1.5-GGUF with Ollama:
```
ollama run hf.co/fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
```

Unsloth Studio new

How to use fridaycandour/PaddleOCR-VL-1.5-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 fridaycandour/PaddleOCR-VL-1.5-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 fridaycandour/PaddleOCR-VL-1.5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fridaycandour/PaddleOCR-VL-1.5-GGUF to start chatting

Docker Model Runner
How to use fridaycandour/PaddleOCR-VL-1.5-GGUF with Docker Model Runner:
```
docker model run hf.co/fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16
```

Lemonade

How to use fridaycandour/PaddleOCR-VL-1.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fridaycandour/PaddleOCR-VL-1.5-GGUF:BF16

Run and chat with the model

lemonade run user.PaddleOCR-VL-1.5-GGUF-BF16

List all available models

lemonade list

These are quantizations of the model PaddleOCR-VL-1.5

Download the latest llama.cpp to use them.

Try to use the best quality you can run.
For the mmproj, try to use the F32 version as it will produce the best results.
F32 > BF16 > F16

Includes chat template fix from https://github.com/ggml-org/llama.cpp/pull/18825

Downloads last month: 139

GGUF

Model size

0.5B params

Architecture

paddleocr

Hardware compatibility

8-bit

16-bit

Model tree for fridaycandour/PaddleOCR-VL-1.5-GGUF

Base model

baidu/ERNIE-4.5-0.3B-Paddle

Finetuned

PaddlePaddle/PaddleOCR-VL-1.5

Quantized

(9)

this model