Instructions to use IntelLabsChina/CAT-Q with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use IntelLabsChina/CAT-Q 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 IntelLabsChina/CAT-Q:Q2_0
# Run inference directly in the terminal:
llama cli -hf IntelLabsChina/CAT-Q:Q2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IntelLabsChina/CAT-Q:Q2_0
# Run inference directly in the terminal:
llama cli -hf IntelLabsChina/CAT-Q:Q2_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 IntelLabsChina/CAT-Q:Q2_0
# Run inference directly in the terminal:
./llama-cli -hf IntelLabsChina/CAT-Q:Q2_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 IntelLabsChina/CAT-Q:Q2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IntelLabsChina/CAT-Q:Q2_0

Use Docker

docker model run hf.co/IntelLabsChina/CAT-Q:Q2_0

LM Studio
Jan
Ollama
How to use IntelLabsChina/CAT-Q with Ollama:
```
ollama run hf.co/IntelLabsChina/CAT-Q:Q2_0
```

Unsloth Studio

How to use IntelLabsChina/CAT-Q 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 IntelLabsChina/CAT-Q 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 IntelLabsChina/CAT-Q to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IntelLabsChina/CAT-Q to start chatting

Docker Model Runner
How to use IntelLabsChina/CAT-Q with Docker Model Runner:
```
docker model run hf.co/IntelLabsChina/CAT-Q:Q2_0
```

Lemonade

How to use IntelLabsChina/CAT-Q with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IntelLabsChina/CAT-Q:Q2_0

Run and chat with the model

lemonade run user.CAT-Q-Q2_0

List all available models

lemonade list

Atomic Chat

Use public Hugging Face model IDs

by genggng - opened 27 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-7

Files changed (7) hide show

llama2-7b/config.yaml +1 -1
qwen3-14B/config.yaml +1 -1
qwen3-32B/config.yaml +1 -1
qwen3-4b/config.yaml +1 -1
qwen3-8b/config.yaml +1 -1
qwen3-moe-235B-A22B/config.yaml +1 -1
qwen3-moe-30B-A3B/config.yaml +1 -1

llama2-7b/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Llama-2-7b-hf
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: meta-llama/Llama-2-7b-hf
 wbits: 1
 abits: 16
 group_size: 128

qwen3-14B/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-14B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-14B
 wbits: 1
 abits: 16
 group_size: 128

qwen3-32B/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-32B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-32B
 wbits: 1
 abits: 16
 group_size: 128

qwen3-4b/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-4B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-4B
 wbits: 1
 abits: 16
 group_size: 128

qwen3-8b/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-8B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-8B
 wbits: 1
 abits: 16
 group_size: 128

qwen3-moe-235B-A22B/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-235B-A22B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-235B-A22B
 wbits: 1
 abits: 16
 group_size: 128

qwen3-moe-30B-A3B/config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 # Model and quantization
-model: model_zoo/Qwen3-30B-A3B
 wbits: 1
 abits: 16
 group_size: 128

 # Model and quantization
+model: Qwen/Qwen3-30B-A3B
 wbits: 1
 abits: 16
 group_size: 128