Instructions to use 754geg/kpok with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 754geg/kpok with Transformers:

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

pipe = pipeline("text-generation", model="754geg/kpok")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("754geg/kpok", dtype="auto")

llama-cpp-python

How to use 754geg/kpok with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="754geg/kpok",
	filename="WizardLM-2-8x22B.IQ1_S.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use 754geg/kpok with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 754geg/kpok:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf 754geg/kpok:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 754geg/kpok:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf 754geg/kpok:IQ1_S

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 754geg/kpok:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf 754geg/kpok:IQ1_S

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 754geg/kpok:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 754geg/kpok:IQ1_S

Use Docker

docker model run hf.co/754geg/kpok:IQ1_S

LM Studio
Jan

vLLM

How to use 754geg/kpok with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "754geg/kpok"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "754geg/kpok",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/754geg/kpok:IQ1_S

SGLang

How to use 754geg/kpok 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 "754geg/kpok" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "754geg/kpok",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "754geg/kpok" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "754geg/kpok",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use 754geg/kpok with Ollama:
```
ollama run hf.co/754geg/kpok:IQ1_S
```

Unsloth Studio new

How to use 754geg/kpok 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 754geg/kpok 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 754geg/kpok to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 754geg/kpok to start chatting

Docker Model Runner
How to use 754geg/kpok with Docker Model Runner:
```
docker model run hf.co/754geg/kpok:IQ1_S
```

Lemonade

How to use 754geg/kpok with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 754geg/kpok:IQ1_S

Run and chat with the model

lemonade run user.kpok-IQ1_S

List all available models

lemonade list

MaziyarPanahi/WizardLM-2-8x22B-GGUF

Model creator: microsoft
Original model: microsoft/WizardLM-2-8x22B

Description

MaziyarPanahi/WizardLM-2-8x22B-GGUF contains GGUF format model files for microsoft/WizardLM-2-8x22B.

How to download

You can download only the quants you need instead of cloning the entire repository as follows:

huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include '*Q2_K*gguf'

On Windows:

huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include *Q4_K_S*gguf

Load sharded model

llama_load_model_from_file will detect the number of files and will load additional tensors from the rest of files.

llama.cpp/main -m WizardLM-2-8x22B.Q2_K-00001-of-00005.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 1024 -e

Prompt template

{system_prompt}
USER: {prompt}
ASSISTANT: </s>

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, 
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: {prompt} ASSISTANT: </s>......

Downloads last month: 7

GGUF

Model size

141B params

Architecture

llama

Hardware compatibility

1-bit

Model tree for 754geg/kpok

Base model

microsoft/WizardLM-2-8x22B

Quantized

(17)

this model