Instructions to use martinkozle/MKLLM-7B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use martinkozle/MKLLM-7B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="martinkozle/MKLLM-7B-Instruct-GGUF",
	filename="MKLLM-7B-Instruct-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use martinkozle/MKLLM-7B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf martinkozle/MKLLM-7B-Instruct-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 martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf martinkozle/MKLLM-7B-Instruct-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 martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf martinkozle/MKLLM-7B-Instruct-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 martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use martinkozle/MKLLM-7B-Instruct-GGUF with Ollama:
```
ollama run hf.co/martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use martinkozle/MKLLM-7B-Instruct-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 martinkozle/MKLLM-7B-Instruct-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 martinkozle/MKLLM-7B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for martinkozle/MKLLM-7B-Instruct-GGUF to start chatting

Docker Model Runner
How to use martinkozle/MKLLM-7B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use martinkozle/MKLLM-7B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull martinkozle/MKLLM-7B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MKLLM-7B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

MKLLM-7B-Instruct-GGUF

GGUF quants of trajkovnikola/MKLLM-7B-Instruct

Script used

from_dir=./MKLLM-7B-Instruct
dir=./MKLLM-7B-Instruct-GGUF
base_precision=BF16
file_base=MKLLM-7B-Instruct

quants=("Q2_K" "Q3_K_S" "Q3_K_M" "Q3_K_L" "Q4_K_S" "Q4_K_M" "Q4_0" "Q4_1" "Q5_K_S" "Q5_K_M" "Q5_0" "Q5_1" "Q6_K" "Q8_0" "IQ3_XS" "IQ3_S" "IQ3_M" "IQ4_XS" "IQ4_NL")


docker run --rm -v "${from_dir}":/repo ghcr.io/ggerganov/llama.cpp:full --convert "/repo" --outtype bf16

mkdir "${dir}"

mv "${from_dir}/ggml-model-bf16.gguf" "${dir}/${file_base}-${base_precision}.gguf"

for quant in ${quants[@]};
do
    echo "###########################"
    echo $quant
    echo "==========================="
    docker run --rm -v "${dir}":/repo ghcr.io/ggerganov/llama.cpp:full --quantize "/repo/${file_base}-${base_precision}.gguf" "/repo/${file_base}-${quant}.gguf" "${quant}"
done

Downloads last month: 71

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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