Instructions to use TabunKaze/Basil-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TabunKaze/Basil-beta with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TabunKaze/Basil-beta", dtype="auto")

llama-cpp-python

How to use TabunKaze/Basil-beta with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TabunKaze/Basil-beta",
	filename="Basil-omni-v2.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TabunKaze/Basil-beta with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TabunKaze/Basil-beta:Q8_0
# Run inference directly in the terminal:
llama-cli -hf TabunKaze/Basil-beta:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TabunKaze/Basil-beta:Q8_0
# Run inference directly in the terminal:
llama-cli -hf TabunKaze/Basil-beta:Q8_0

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 TabunKaze/Basil-beta:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf TabunKaze/Basil-beta:Q8_0

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 TabunKaze/Basil-beta:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TabunKaze/Basil-beta:Q8_0

Use Docker

docker model run hf.co/TabunKaze/Basil-beta:Q8_0

LM Studio
Jan
Ollama
How to use TabunKaze/Basil-beta with Ollama:
```
ollama run hf.co/TabunKaze/Basil-beta:Q8_0
```

Unsloth Studio new

How to use TabunKaze/Basil-beta 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 TabunKaze/Basil-beta 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 TabunKaze/Basil-beta to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TabunKaze/Basil-beta to start chatting

Docker Model Runner
How to use TabunKaze/Basil-beta with Docker Model Runner:
```
docker model run hf.co/TabunKaze/Basil-beta:Q8_0
```

Lemonade

How to use TabunKaze/Basil-beta with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TabunKaze/Basil-beta:Q8_0

Run and chat with the model

lemonade run user.Basil-beta-Q8_0

List all available models

lemonade list

Basil-beta / README.md

TabunKaze

Unsloth Model Card

0ea4d1c verified 11 months ago

preview code

raw

history blame contribute delete

576 Bytes

metadata

base_model: unsloth/gemma-3n-E4B-it
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma3n
license: apache-2.0
language:
  - en

Uploaded finetuned model

Developed by: TabunKaze
License: apache-2.0
Finetuned from model : unsloth/gemma-3n-E4B-it

This gemma3n model was trained 2x faster with Unsloth and Huggingface's TRL library.