Instructions to use IkariDev/IkariTest2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IkariDev/IkariTest2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="IkariDev/IkariTest2-GGUF",
	filename="IkariTest2.3_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/IkariTest2-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/IkariTest2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf IkariDev/IkariTest2-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 IkariDev/IkariTest2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf IkariDev/IkariTest2-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 IkariDev/IkariTest2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf IkariDev/IkariTest2-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 IkariDev/IkariTest2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IkariDev/IkariTest2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/IkariDev/IkariTest2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use IkariDev/IkariTest2-GGUF with Ollama:
```
ollama run hf.co/IkariDev/IkariTest2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use IkariDev/IkariTest2-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/IkariTest2-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/IkariTest2-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/IkariTest2-GGUF to start chatting

Docker Model Runner
How to use IkariDev/IkariTest2-GGUF with Docker Model Runner:
```
docker model run hf.co/IkariDev/IkariTest2-GGUF:Q4_K_M
```

Lemonade

How to use IkariDev/IkariTest2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IkariDev/IkariTest2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.IkariTest2-GGUF-Q4_K_M

List all available models

lemonade list

Findings

by xpgx1 - opened Mar 18, 2024

Discussion

xpgx1

Mar 18, 2024

Rather clever, rather attentive - just entirely mad most of the time =)

Whatever this is, it's clearly "broken", but sometimes it surpasses anything a 13b has ever done for me ^-^

I tested with ChatML tho, perhaps a proper format might do the trick. I'm very interested in getting my hands on your newest model. With or without the others. Athenav4 is still my most beloved one 😎

IkariDev

Owner Mar 18, 2024

The format you are supposed to use is NsChatML(custom chatml made by Neversleep(Me and undi), it means NeverSleepChatML), if you wanna talk about the model you can either do on our server or in my discord dm's.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment