Instructions to use RichardErkhov/Sparkoo_-_KateAI-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Sparkoo_-_KateAI-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/Sparkoo_-_KateAI-gguf",
	filename="KateAI.IQ3_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/Sparkoo_-_KateAI-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/Sparkoo_-_KateAI-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 RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/Sparkoo_-_KateAI-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 RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/Sparkoo_-_KateAI-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 RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/Sparkoo_-_KateAI-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/Sparkoo_-_KateAI-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 RichardErkhov/Sparkoo_-_KateAI-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 RichardErkhov/Sparkoo_-_KateAI-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/Sparkoo_-_KateAI-gguf to start chatting

Docker Model Runner
How to use RichardErkhov/Sparkoo_-_KateAI-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/Sparkoo_-_KateAI-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/Sparkoo_-_KateAI-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Sparkoo_-_KateAI-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

KateAI - GGUF

Model creator: https://huggingface.co/Sparkoo/
Original model: https://huggingface.co/Sparkoo/KateAI/

Name	Quant method	Size
KateAI.Q2_K.gguf	Q2_K	0.05GB
KateAI.IQ3_XS.gguf	IQ3_XS	0.06GB
KateAI.IQ3_S.gguf	IQ3_S	0.06GB
KateAI.Q3_K_S.gguf	Q3_K_S	0.06GB
KateAI.IQ3_M.gguf	IQ3_M	0.06GB
KateAI.Q3_K.gguf	Q3_K	0.06GB
KateAI.Q3_K_M.gguf	Q3_K_M	0.06GB
KateAI.Q3_K_L.gguf	Q3_K_L	0.06GB
KateAI.IQ4_XS.gguf	IQ4_XS	0.07GB
KateAI.Q4_0.gguf	Q4_0	0.07GB
KateAI.IQ4_NL.gguf	IQ4_NL	0.07GB
KateAI.Q4_K_S.gguf	Q4_K_S	0.07GB
KateAI.Q4_K.gguf	Q4_K	0.08GB
KateAI.Q4_K_M.gguf	Q4_K_M	0.08GB
KateAI.Q4_1.gguf	Q4_1	0.08GB
KateAI.Q5_0.gguf	Q5_0	0.09GB
KateAI.Q5_K_S.gguf	Q5_K_S	0.09GB
KateAI.Q5_K.gguf	Q5_K	0.09GB
KateAI.Q5_K_M.gguf	Q5_K_M	0.09GB
KateAI.Q5_1.gguf	Q5_1	0.1GB
KateAI.Q6_K.gguf	Q6_K	0.1GB
KateAI.Q8_0.gguf	Q8_0	0.14GB

Original model description:

language: - en pipeline_tag: text-generation

Warning!!

This model is in the process of being moved from gpt2 architecture -> a custom architecture. Note that it may not work at certain times because of the moving. Thank you for understanding.

Kate

This is a custom model for text generation.

Model Details

model_type: custom_transformer

Downloads last month: 36

GGUF

Model size

0.1B params

Architecture

kateai

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support