Instructions to use XeroCodes/aurora-12b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use XeroCodes/aurora-12b-gguf with PEFT:
```
Task type is invalid.
```

How to use XeroCodes/aurora-12b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XeroCodes/aurora-12b-gguf",
	filename="aurora-12b-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/aurora-12b-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/aurora-12b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/aurora-12b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XeroCodes/aurora-12b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf XeroCodes/aurora-12b-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/aurora-12b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf XeroCodes/aurora-12b-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/aurora-12b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XeroCodes/aurora-12b-gguf:F16

Use Docker

docker model run hf.co/XeroCodes/aurora-12b-gguf:F16

LM Studio
Jan

vLLM

How to use XeroCodes/aurora-12b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XeroCodes/aurora-12b-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/aurora-12b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XeroCodes/aurora-12b-gguf:F16

Ollama
How to use XeroCodes/aurora-12b-gguf with Ollama:
```
ollama run hf.co/XeroCodes/aurora-12b-gguf:F16
```

Unsloth Studio new

How to use XeroCodes/aurora-12b-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/aurora-12b-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/aurora-12b-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/aurora-12b-gguf to start chatting

Docker Model Runner
How to use XeroCodes/aurora-12b-gguf with Docker Model Runner:
```
docker model run hf.co/XeroCodes/aurora-12b-gguf:F16
```

Lemonade

How to use XeroCodes/aurora-12b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XeroCodes/aurora-12b-gguf:F16

Run and chat with the model

lemonade run user.aurora-12b-gguf-F16

List all available models

lemonade list

Aurora-12B

Aurora-12B is a powerful language model fine-tuned from the Mistral-Nemo-Instruct-2407 base model, designed specifically for code generation and understanding tasks. This model leverages the extensive iamtarun/code_instructions_120k_alpaca dataset to provide high-quality code-related instructions and solutions.

Overview

Aurora-12B is tailored for developers and researchers who need advanced code completion, code understanding, and programming assistance. It understands a wide variety of programming languages and can provide accurate and contextually relevant suggestions.

Features

Code Generation: Generate code snippets in various programming languages.
Code Completion: Complete partial code fragments.
Code Understanding: Explain code functionality and provide comments.
Instruction Following: Follow and execute code-related instructions with high accuracy.

Model Details

Base Model: Mistral-Nemo-Instruct-2407
Fine-Tuned On: iamtarun/code_instructions_120k_alpaca
Parameters: 12 billion

Dataset

The model was fine-tuned on the iamtarun/code_instructions_120k_alpaca dataset, which includes 120,000 examples of code instructions and solutions. This diverse dataset ensures that the model can handle a wide range of coding scenarios.

Downloads last month: 19

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

32-bit

Model tree for XeroCodes/aurora-12b-gguf

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Adapter

(66)

this model

XeroCodes
/

aurora-12b-gguf