Instructions to use noctrex/LightOnOCR-2-1B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use noctrex/LightOnOCR-2-1B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

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 noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

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 noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use noctrex/LightOnOCR-2-1B-GGUF with Ollama:
```
ollama run hf.co/noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
```

Unsloth Studio

How to use noctrex/LightOnOCR-2-1B-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 noctrex/LightOnOCR-2-1B-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 noctrex/LightOnOCR-2-1B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for noctrex/LightOnOCR-2-1B-GGUF to start chatting

Docker Model Runner
How to use noctrex/LightOnOCR-2-1B-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M
```

Lemonade

How to use noctrex/LightOnOCR-2-1B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/LightOnOCR-2-1B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LightOnOCR-2-1B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Embedded images?

by coder543 - opened Feb 23

Discussion

coder543

Feb 23

Sometimes the markdown output will contain things like ![image](image_1.png), but I don't see any way to know what that should be. Is the model supposed to be outputting coordinates that I can use to crop out sections of the input image? I believe that's how it is supposed to work, but I'm not seeing that with the gguf version using llama-server.

noctrex

Owner Feb 23

I primarily use it only for strictly OCR tasks, so unfortunately I do not know why it produces this output. Maybe this works only on their own harness and not with llama

coder543 changed discussion status to closed Feb 23

coder543 changed discussion status to open Feb 23

coder543

Feb 23

To clarify, this is during the OCR task when the model sees something important that it can’t transcribe, like a chart or an image within a document.

If you don’t know how, that’s okay, I just wondered.

(I accidentally hit close… oops. I was intending to leave this open in case someone else knows.)

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

Tap or paste here to upload images

· Sign up or log in to comment