Instructions to use redponike/KAT-Dev-72B-Exp-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redponike/KAT-Dev-72B-Exp-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="redponike/KAT-Dev-72B-Exp-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("redponike/KAT-Dev-72B-Exp-GGUF", dtype="auto")

llama-cpp-python

How to use redponike/KAT-Dev-72B-Exp-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="redponike/KAT-Dev-72B-Exp-GGUF",
	filename="KAT-Dev-72B-Exp-IQ2_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use redponike/KAT-Dev-72B-Exp-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf redponike/KAT-Dev-72B-Exp-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 redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf redponike/KAT-Dev-72B-Exp-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 redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Use Docker

docker model run hf.co/redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use redponike/KAT-Dev-72B-Exp-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redponike/KAT-Dev-72B-Exp-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/KAT-Dev-72B-Exp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

SGLang

How to use redponike/KAT-Dev-72B-Exp-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "redponike/KAT-Dev-72B-Exp-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/KAT-Dev-72B-Exp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "redponike/KAT-Dev-72B-Exp-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/KAT-Dev-72B-Exp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use redponike/KAT-Dev-72B-Exp-GGUF with Ollama:
```
ollama run hf.co/redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
```

Unsloth Studio new

How to use redponike/KAT-Dev-72B-Exp-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 redponike/KAT-Dev-72B-Exp-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 redponike/KAT-Dev-72B-Exp-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for redponike/KAT-Dev-72B-Exp-GGUF to start chatting

Pi new

How to use redponike/KAT-Dev-72B-Exp-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use redponike/KAT-Dev-72B-Exp-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use redponike/KAT-Dev-72B-Exp-GGUF with Docker Model Runner:
```
docker model run hf.co/redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M
```

Lemonade

How to use redponike/KAT-Dev-72B-Exp-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull redponike/KAT-Dev-72B-Exp-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KAT-Dev-72B-Exp-GGUF-Q4_K_M

List all available models

lemonade list

GGUF quants of Kwaipilot/KAT-Dev-72B-Exp

Using llama.cpp b6730 (commit e60f01d941bc5b7fae62dd57fee4cec76ec0ea6e)

The importance matrix was generated with calibration_datav3.txt.

All quants were generated/calibrated with the imatrix, including the K quants.

News

🔥 We’re thrilled to announce the release of KAT-Dev-72B-Exp, our latest and most powerful model yet!

🔥 You can now try our strongest proprietary coder model KAT-Coder directly on the StreamLake platform for free.

Highlights

KAT-Dev-72B-Exp is an open-source 72B-parameter model for software engineering tasks.

On SWE-Bench Verified, KAT-Dev-72B-Exp achieves 74.6% accuracy ⚡ — when evaluated strictly with the SWE-agent scaffold.

KAT-Dev-72B-Exp is the experimental reinforcement-learning version of the KAT-Coder model. Through this open-source release, we aim to reveal the technical innovations behind KAT-Coder’s large-scale RL to developers and researchers.

Introduction

We rewrote the attention kernel and redesigned the training engine for shared prefix trajectories to achieve highly efficient RL training, especially for scaffolds leveraging context management.

Furthermore, to prevent exploration collapse observed in RL training, we reshaped advantage distribution based on pass rates: amplifying the advantage scale of highly exploratory groups while reducing that of low-exploration ones.

SWE agent Evaluation Parameters

temperature: 0.6
max_turns: 150
history_processors.n: 100

For full settings please refer to inference.yaml

Downloads last month: 3

GGUF

Model size

73B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for redponike/KAT-Dev-72B-Exp-GGUF

Base model

Kwaipilot/KAT-Dev-72B-Exp

Quantized

(17)

this model