Instructions to use IkariDev/Athena-v4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IkariDev/Athena-v4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="IkariDev/Athena-v4-GGUF",
	filename="Athena-v4.Q3_K_L.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use IkariDev/Athena-v4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IkariDev/Athena-v4-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf IkariDev/Athena-v4-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IkariDev/Athena-v4-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf IkariDev/Athena-v4-GGUF:Q4_K_S

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 IkariDev/Athena-v4-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf IkariDev/Athena-v4-GGUF:Q4_K_S

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 IkariDev/Athena-v4-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IkariDev/Athena-v4-GGUF:Q4_K_S

Use Docker

docker model run hf.co/IkariDev/Athena-v4-GGUF:Q4_K_S

LM Studio
Jan
Ollama
How to use IkariDev/Athena-v4-GGUF with Ollama:
```
ollama run hf.co/IkariDev/Athena-v4-GGUF:Q4_K_S
```

Unsloth Studio new

How to use IkariDev/Athena-v4-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 IkariDev/Athena-v4-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 IkariDev/Athena-v4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IkariDev/Athena-v4-GGUF to start chatting

Docker Model Runner
How to use IkariDev/Athena-v4-GGUF with Docker Model Runner:
```
docker model run hf.co/IkariDev/Athena-v4-GGUF:Q4_K_S
```

Lemonade

How to use IkariDev/Athena-v4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IkariDev/Athena-v4-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Athena-v4-GGUF-Q4_K_S

List all available models

lemonade list

Experimental Athena v4 model. Use Alpaca format. Suitable for RP, ERP and general stuff.

I should state here that this is a HIGHLY experimental model!

Description

This repo contains GGUF files of Athena-V4.

fp16 - by IkariDev+Undi95

OLD(GGUF - by IkariDev+Undi95)

Ratings:

Note: I have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!

If you want your rating to be here, send me a message over on DC and ill put up a screenshot of it here. DC name is "ikaridev".

Models+loras used and recipe

Athena-v3
Xwin-LM/Xwin-LM-13B-V0.1
Undi95/PsyMedRP-v1-13B
cgato/Thespis-13b-v0.2
jondurbin/airoboros-l2-13b-3.0

Athena-v4-tmp1 = [ Athena-v3(0.85)+Xwin-LM/Xwin-LM-13B-V0.1(0.15) ]
Athena-v4-tmp2 = [ Undi95/PsyMedRP-v1-13B(0.55)+cgato/Thespis-13b-v0.2(0.45) ]

Athena-v4-tmp3 = Athena-v4-tmp1(0.55) + Athena-v4-tmp2(0.35)

Athena-v4 = Athena-v4-tmp3 + jondurbin/airoboros-l2-13b-3.0(0.1)

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Thanks to Undi95 for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend.

Downloads last month: 66

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

Inference Providers NEW

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