Instructions to use embedme/OpenReason-ModernColBERT-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 embedme/OpenReason-ModernColBERT-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 embedme/OpenReason-ModernColBERT-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf embedme/OpenReason-ModernColBERT-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf embedme/OpenReason-ModernColBERT-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf embedme/OpenReason-ModernColBERT-GGUF:Q8_0

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 embedme/OpenReason-ModernColBERT-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf embedme/OpenReason-ModernColBERT-GGUF:Q8_0

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 embedme/OpenReason-ModernColBERT-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf embedme/OpenReason-ModernColBERT-GGUF:Q8_0

Use Docker

docker model run hf.co/embedme/OpenReason-ModernColBERT-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use embedme/OpenReason-ModernColBERT-GGUF with Ollama:
```
ollama run hf.co/embedme/OpenReason-ModernColBERT-GGUF:Q8_0
```

Unsloth Studio

How to use embedme/OpenReason-ModernColBERT-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 embedme/OpenReason-ModernColBERT-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 embedme/OpenReason-ModernColBERT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for embedme/OpenReason-ModernColBERT-GGUF to start chatting

Docker Model Runner
How to use embedme/OpenReason-ModernColBERT-GGUF with Docker Model Runner:
```
docker model run hf.co/embedme/OpenReason-ModernColBERT-GGUF:Q8_0
```

Lemonade

How to use embedme/OpenReason-ModernColBERT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull embedme/OpenReason-ModernColBERT-GGUF:Q8_0

Run and chat with the model

lemonade run user.OpenReason-ModernColBERT-GGUF-Q8_0

List all available models

lemonade list

Atomic Chat

ctrltokyo commited on Mar 21

Commit

80b37cd

verified ·

1 Parent(s): ebf96ad

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +32 -0

README.md ADDED Viewed

	@@ -0,0 +1,32 @@

+---
+tags:
+- gguf
+- modernbert
+- colbert
+- reasoning
+- late-interaction
+license: apache-2.0
+base_model: ctrltokyo/OpenReason-ModernColBERT
+---
+# OpenReason-ModernColBERT GGUF
+GGUF conversion of [ctrltokyo/OpenReason-ModernColBERT](https://huggingface.co/ctrltokyo/OpenReason-ModernColBERT) for use with [litembeddings](https://github.com/alexandernicholson/litembeddings).
+## Files
+| File | Size | Description |
+|------|------|-------------|
+| openreason-moderncolbert-Q8_0.gguf | 153M | Q8_0 quantized ModernBERT encoder |
+| openreason-moderncolbert-Q8_0.projection | 385K | ColBERT 768 to 128 linear projection |
+## Usage with litembeddings
+## Source Model
+- Architecture: ModernBERT (150M params)
+- Training: Fine-tuned on BRIGHT benchmark reasoning tasks
+- Base: lightonai/GTE-ModernColBERT-v1
+- License: Apache 2.0