Instructions to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF",
	filename="ArliAI-Llama-3-8B-Cumulus-v0.3.2.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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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": "QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M

Ollama
How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-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 QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF-Q4_K_M

List all available models

lemonade list

OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF

This is quantized version of OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF created using llama.cpp

Model Description

Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct

This v0.3.2 version is even more uncensored thanks to using https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated as the base model. The 0.0.2 is for slight adjustment to the DPO stage.

In terms of reasoning and intelligence, this model is probably a bit worse than the OG model because of the decensoring. However, this model is better at long back and forth chats and will refuse less.

This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character.

Training:

Full 8192 sequence length.
Training duration is around 2 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 64-alpha resulting in ~2% trainable weights.

Instruct format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Quants:

FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2

GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF