Instructions to use XeroCodes/xenith-2b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use XeroCodes/xenith-2b-gguf with PEFT:
```
Task type is invalid.
```

How to use XeroCodes/xenith-2b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XeroCodes/xenith-2b-gguf",
	filename="xenith-2b-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/xenith-2b-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/xenith-2b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/xenith-2b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XeroCodes/xenith-2b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/xenith-2b-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/xenith-2b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf XeroCodes/xenith-2b-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/xenith-2b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XeroCodes/xenith-2b-gguf:F16

Use Docker

docker model run hf.co/XeroCodes/xenith-2b-gguf:F16

LM Studio
Jan

vLLM

How to use XeroCodes/xenith-2b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XeroCodes/xenith-2b-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/xenith-2b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XeroCodes/xenith-2b-gguf:F16

Ollama
How to use XeroCodes/xenith-2b-gguf with Ollama:
```
ollama run hf.co/XeroCodes/xenith-2b-gguf:F16
```

Unsloth Studio new

How to use XeroCodes/xenith-2b-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/xenith-2b-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/xenith-2b-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/xenith-2b-gguf to start chatting

Docker Model Runner
How to use XeroCodes/xenith-2b-gguf with Docker Model Runner:
```
docker model run hf.co/XeroCodes/xenith-2b-gguf:F16
```

Lemonade

How to use XeroCodes/xenith-2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XeroCodes/xenith-2b-gguf:F16

Run and chat with the model

lemonade run user.xenith-2b-gguf-F16

List all available models

lemonade list

Xenith

Welcome to the Xenith Model repository! This model is fine-tuned for advanced text generation tasks, built on top of the unsloth/gemma-1.1-2b-it-bnb-4bit base model, and further enhanced using the ssbuild/alpaca_flan-muffin dataset. The model is designed to provide high-quality and coherent text generation in English.

Introduction

The Xenith Model is a powerful text generation model built using the PEFT (Parameter-Efficient Fine-Tuning) library. It leverages the strengths of the unsloth/gemma-1.1-2b-it-bnb-4bit model and is fine-tuned on the ssbuild/alpaca_flan-muffin dataset. Xenith is designed to perform well across a variety of text generation tasks, delivering consistent and high-quality outputs.

Features

Efficient Text Generation: Powered by a 2 billion parameter model optimized for text generation tasks.
Fine-Tuned Performance: Enhanced through fine-tuning on the ssbuild/alpaca_flan-muffin dataset for better contextual understanding and response accuracy.
Compact and Fast: Uses 4-bit quantization for faster inference and lower memory usage without compromising quality.
Open Source: Licensed under the Apache-2.0 license, making it free to use, modify, and distribute.

Model Details

Base Model: unsloth/gemma-1.1-2b-it-bnb-4bit
Fine-tuning Dataset: ssbuild/alpaca_flan-muffin
Language: English
Library: PEFT (Parameter-Efficient Fine-Tuning)
License: Apache-2.0

Dataset

The Xenith Model is fine-tuned using the ssbuild/alpaca_flan-muffin dataset. This dataset is known for its diverse and high-quality examples, making it ideal for training models that require nuanced understanding and contextual accuracy.

Downloads last month: 15

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

8-bit

16-bit

32-bit

Model tree for XeroCodes/xenith-2b-gguf

Base model

unsloth/gemma-1.1-2b-it-bnb-4bit

Adapter

(9)

this model

XeroCodes
/

xenith-2b-gguf