Instructions to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF",
	filename="aurelian-alpha0.1_Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Noeda/aurelian-alpha0.1-70b-rope8-32K-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 Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Noeda/aurelian-alpha0.1-70b-rope8-32K-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 Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Noeda/aurelian-alpha0.1-70b-rope8-32K-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 Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with Ollama:
```
ollama run hf.co/Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
```

Unsloth Studio

How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-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 Noeda/aurelian-alpha0.1-70b-rope8-32K-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 Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF to start chatting

Docker Model Runner
How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with Docker Model Runner:
```
docker model run hf.co/Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M
```

Lemonade

How to use Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Noeda/aurelian-alpha0.1-70b-rope8-32K-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.aurelian-alpha0.1-70b-rope8-32K-GGUF-Q4_K_M

List all available models

lemonade list

This repository contains .gguf files for:

https://huggingface.co/grimulkan/aurelian-alpha0.1-70b-rope8-32K-fp16

Made with llama.cpp commit e18f7345a300920e234f732077bda660cc6cda9c

IMPORTANT: Linear Rope Scaling = 8 (IMPORTANT: use a factor of 8 even if you are not using the full 32K context length). The setting typically defaults to 1, so you need to change it.

md5sums

aurelian-alpha0.1_Q4_K_M.gguf 27ba8b8dc99776cc48d667d1766f8771
aurelian-alpha0.1_Q6_K.gguf ab36ed3f2cfd2f833cb814304a5cbe50

The aurelian-alpha0.1_Q6_K.gguf is just barely over 50G, HuggingFace's file limit, so it is in two parts.

On a UNIX-like system, you can use cat to piece it together:

cat aurelian-alpha0.1_Q6_K.gguf-split-a aurelian-alpha0.1_Q6_K.gguf-split-b > aurelian-alpha0.1_Q6_K.gguf

Downloads last month: 3

GGUF

Model size

69B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support