Instructions to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF",
	filename="KONI-Llama3-8B-Instruct-20240729-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

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 tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

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 tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/KONI-Llama3-8B-Instruct-20240729-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": "tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

Ollama
How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with Ollama:
```
ollama run hf.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-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 tensorblock/KONI-Llama3-8B-Instruct-20240729-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 tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K
```

Lemonade

How to use tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF:Q2_K

Run and chat with the model

lemonade run user.KONI-Llama3-8B-Instruct-20240729-GGUF-Q2_K

List all available models

lemonade list

KONI-Llama3-8B-Instruct-20240729-GGUF / README.md

morriszms

Upload folder using huggingface_hub

4c613e7 verified over 1 year ago

preview code

Raw

History Blame

5.97 kB

	---
	language: ko
	pipeline_tag: text-generation
	license: llama3
	tags:
	- TensorBlock
	- GGUF
	base_model: KISTI-KONI/KONI-Llama3-8B-Instruct-20240729
	---

	<div style="width: auto; margin-left: auto; margin-right: auto">
	<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
	</div>
	<div style="display: flex; justify-content: space-between; width: 100%;">
	<div style="display: flex; flex-direction: column; align-items: flex-start;">
	<p style="margin-top: 0.5em; margin-bottom: 0em;">
	Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
	</p>
	</div>
	</div>

	## KISTI-KONI/KONI-Llama3-8B-Instruct-20240729 - GGUF

	This repo contains GGUF format model files for [KISTI-KONI/KONI-Llama3-8B-Instruct-20240729](https://huggingface.co/KISTI-KONI/KONI-Llama3-8B-Instruct-20240729).

	The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).

	<div style="text-align: left; margin: 20px 0;">
	<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
	Run them on the TensorBlock client using your local machine ↗
	</a>
	</div>

	## Prompt template

	```
	<\|start_header_id\|>system<\|end_header_id\|>

	You are KONI, an AI assistant trained based on LlaMA3 and created by KISTI to be helpful and honest. Your knowledge spans a wide range of topics, allowing you to engage in substantive conversations and provide analysis on complex subjects. Below is an instruction that describes a task. Write a response that appropriately completes the request. If you don't know the answer, just say that you don't know.<\|eot_id\|><\|start_header_id\|>system<\|end_header_id\|>

	{system_prompt}<\|eot_id\|><\|start_header_id\|>Human<\|end_header_id\|>

	{prompt}<\|eot_id\|><\|start_header_id\|>KONI<\|end_header_id\|>
	```

	## Model file specification

	\| Filename \| Quant type \| File Size \| Description \|
	\| -------- \| ---------- \| --------- \| ----------- \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q2_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q2_K.gguf) \| Q2_K \| 3.179 GB \| smallest, significant quality loss - not recommended for most purposes \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q3_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q3_K_S.gguf) \| Q3_K_S \| 3.665 GB \| very small, high quality loss \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q3_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q3_K_M.gguf) \| Q3_K_M \| 4.019 GB \| very small, high quality loss \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q3_K_L.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q3_K_L.gguf) \| Q3_K_L \| 4.322 GB \| small, substantial quality loss \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q4_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q4_0.gguf) \| Q4_0 \| 4.661 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q4_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q4_K_S.gguf) \| Q4_K_S \| 4.693 GB \| small, greater quality loss \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q4_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q4_K_M.gguf) \| Q4_K_M \| 4.921 GB \| medium, balanced quality - recommended \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q5_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q5_0.gguf) \| Q5_0 \| 5.599 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q5_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q5_K_S.gguf) \| Q5_K_S \| 5.599 GB \| large, low quality loss - recommended \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q5_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q5_K_M.gguf) \| Q5_K_M \| 5.733 GB \| large, very low quality loss - recommended \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q6_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q6_K.gguf) \| Q6_K \| 6.596 GB \| very large, extremely low quality loss \|
	\| [KONI-Llama3-8B-Instruct-20240729-Q8_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF/blob/main/KONI-Llama3-8B-Instruct-20240729-Q8_0.gguf) \| Q8_0 \| 8.541 GB \| very large, extremely low quality loss - not recommended \|


	## Downloading instruction

	### Command line

	Firstly, install Huggingface Client

	```shell
	pip install -U "huggingface_hub[cli]"
	```

	Then, downoad the individual model file the a local directory

	```shell
	huggingface-cli download tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF --include "KONI-Llama3-8B-Instruct-20240729-Q2_K.gguf" --local-dir MY_LOCAL_DIR
	```

	If you wanna download multiple model files with a pattern (e.g., `Q4_Kgguf`), you can try:

	```shell
	huggingface-cli download tensorblock/KONI-Llama3-8B-Instruct-20240729-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='Q4_Kgguf'
	```