Instructions to use XeroCodes/xander-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use XeroCodes/xander-gguf with PEFT:
```
Task type is invalid.
```

How to use XeroCodes/xander-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XeroCodes/xander-gguf",
	filename="xander-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use XeroCodes/xander-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XeroCodes/xander-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/xander-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XeroCodes/xander-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/xander-gguf:F16

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 XeroCodes/xander-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf XeroCodes/xander-gguf:F16

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 XeroCodes/xander-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XeroCodes/xander-gguf:F16

Use Docker

docker model run hf.co/XeroCodes/xander-gguf:F16

LM Studio
Jan

vLLM

How to use XeroCodes/xander-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XeroCodes/xander-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": "XeroCodes/xander-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XeroCodes/xander-gguf:F16

Ollama
How to use XeroCodes/xander-gguf with Ollama:
```
ollama run hf.co/XeroCodes/xander-gguf:F16
```

Unsloth Studio new

How to use XeroCodes/xander-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 XeroCodes/xander-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 XeroCodes/xander-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for XeroCodes/xander-gguf to start chatting

Docker Model Runner
How to use XeroCodes/xander-gguf with Docker Model Runner:
```
docker model run hf.co/XeroCodes/xander-gguf:F16
```

Lemonade

How to use XeroCodes/xander-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XeroCodes/xander-gguf:F16

Run and chat with the model

lemonade run user.xander-gguf-F16

List all available models

lemonade list

Xander

Welcome to the Xander Conversational Model repository! This model has been fine-tuned from the unsloth/llama-2-7b-chat-bnb-4bit base on the piotr25691/ultrachat-200k-alpaca dataset to enhance its conversational abilities. It is designed to provide more natural, engaging, and contextually aware responses.

Introduction

The Xander Conversational Model is an advanced NLP model aimed at improving interactive text generation. By leveraging the strengths of unsloth/llama-2-7b-chat-bnb-4bit and fine-tuning it with the extensive piotr25691/ultrachat-200k-alpaca dataset, the model is adept at generating coherent and contextually relevant conversations.

Features

Improved Conversational Flow: Generates more natural and engaging responses.
Context Awareness: Maintains context over multiple interactions.
Customizable: Can be further fine-tuned for specific applications or industries.

Dataset

The model was fine-tuned on the piotr25691/ultrachat-200k-alpaca dataset, which consists of 200,000 high-quality conversational pairs. This dataset helps the model to understand and generate more nuanced and contextually appropriate responses.

Performance

The model has shown significant improvements in generating more human-like responses compared to its base. Here are some key metrics:

Perplexity: Lower perplexity indicating better language modeling performance.
Response Coherence: Improved coherence in multi-turn conversations.
Engagement: Higher user satisfaction in interactive scenarios.

Downloads last month: 19

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

32-bit

Model tree for XeroCodes/xander-gguf

Base model

unsloth/llama-2-7b-chat-bnb-4bit

Adapter

(16)

this model