Instructions to use llmware/bonchon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/bonchon with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/bonchon", dtype="auto")

llama-cpp-python

How to use llmware/bonchon with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/bonchon",
	filename="llama-031-instruct.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 llmware/bonchon with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bonchon:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmware/bonchon:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bonchon:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmware/bonchon: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 llmware/bonchon:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llmware/bonchon: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 llmware/bonchon:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/bonchon:Q4_K_M

Use Docker

docker model run hf.co/llmware/bonchon:Q4_K_M

LM Studio
Jan
Ollama
How to use llmware/bonchon with Ollama:
```
ollama run hf.co/llmware/bonchon:Q4_K_M
```

Unsloth Studio new

How to use llmware/bonchon 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 llmware/bonchon 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 llmware/bonchon to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use llmware/bonchon with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf llmware/bonchon: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": "bonchon"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use llmware/bonchon with Docker Model Runner:
```
docker model run hf.co/llmware/bonchon:Q4_K_M
```

Lemonade

How to use llmware/bonchon with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/bonchon:Q4_K_M

Run and chat with the model

lemonade run user.bonchon-Q4_K_M

List all available models

lemonade list

This repository includes some of our favorite bonchon ('side dishes' in Korean).

We currently include in this repository several of our favorite GGUF files from TheBloke, including four of our favorite 7B chat models, in Q4_K_M GGUF files.

This repository is Public, but intended primarily for use in conjunction with other llmware models, datasets and libraries.

Please note specific licensing information and reference for files included in the repository:

HuggingFaceH4/Zephyr-7B-GGUF - MIT License - original repository link
Teknium/OpenHermes-2.5-Mistral-7B-GGUF - Apache 2.0 License - original repository link
Llama2-Chat-7B-GGUF - Llama2 License - original repository link
Starling-7B-GGUF - CC-BY-NC-4.0 License - Non-Commercial - original repository link
EleutherAI/Llema-7B-GGUF - Apache 2.0 License - original repository link

Please also see TheBloke for more information on GGUF.

Downloads last month: 112

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

View +7 variants

Inference Providers NEW

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