Instructions to use lm-kit/lightonocr-2-1b-lmk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lm-kit/lightonocr-2-1b-lmk 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 lm-kit/lightonocr-2-1b-lmk:F16
# Run inference directly in the terminal:
llama cli -hf lm-kit/lightonocr-2-1b-lmk:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lm-kit/lightonocr-2-1b-lmk:F16
# Run inference directly in the terminal:
llama cli -hf lm-kit/lightonocr-2-1b-lmk:F16

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 lm-kit/lightonocr-2-1b-lmk:F16
# Run inference directly in the terminal:
./llama-cli -hf lm-kit/lightonocr-2-1b-lmk:F16

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 lm-kit/lightonocr-2-1b-lmk:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lm-kit/lightonocr-2-1b-lmk:F16

Use Docker

docker model run hf.co/lm-kit/lightonocr-2-1b-lmk:F16

LM Studio
Jan
Ollama
How to use lm-kit/lightonocr-2-1b-lmk with Ollama:
```
ollama run hf.co/lm-kit/lightonocr-2-1b-lmk:F16
```

Unsloth Studio

How to use lm-kit/lightonocr-2-1b-lmk 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 lm-kit/lightonocr-2-1b-lmk 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 lm-kit/lightonocr-2-1b-lmk to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lm-kit/lightonocr-2-1b-lmk to start chatting

Docker Model Runner
How to use lm-kit/lightonocr-2-1b-lmk with Docker Model Runner:
```
docker model run hf.co/lm-kit/lightonocr-2-1b-lmk:F16
```

Lemonade

How to use lm-kit/lightonocr-2-1b-lmk with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lm-kit/lightonocr-2-1b-lmk:F16

Run and chat with the model

lemonade run user.lightonocr-2-1b-lmk-F16

List all available models

lemonade list

Atomic Chat

lcarrere commited on 12 days ago

Commit

f3428a0

verified ·

1 Parent(s): 92e3c37

Add lightonocr-2-1b-F16.gguf (full-precision training base)

Browse files

Files changed (2) hide show

.gitattributes +1 -0
lightonocr-2-1b-F16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 lightonocr-2-1b-Q4_K_M.lmk filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 lightonocr-2-1b-Q4_K_M.lmk filter=lfs diff=lfs merge=lfs -text
+lightonocr-2-1b-F16.gguf filter=lfs diff=lfs merge=lfs -text

lightonocr-2-1b-F16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:524ecfb7fd326cde2285e2a2b887470b582cebf88d9941a214c0a2828f028145
+size 1198178720