Instructions to use aaro765/BanGemmaBTP-BanBTPV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaro765/BanGemmaBTP-BanBTPV2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aaro765/BanGemmaBTP-BanBTPV2",
	filename="BanBTPV2/banbtpv2-00001-of-00016.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 aaro765/BanGemmaBTP-BanBTPV2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aaro765/BanGemmaBTP-BanBTPV2
# Run inference directly in the terminal:
llama-cli -hf aaro765/BanGemmaBTP-BanBTPV2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aaro765/BanGemmaBTP-BanBTPV2
# Run inference directly in the terminal:
llama-cli -hf aaro765/BanGemmaBTP-BanBTPV2

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 aaro765/BanGemmaBTP-BanBTPV2
# Run inference directly in the terminal:
./llama-cli -hf aaro765/BanGemmaBTP-BanBTPV2

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 aaro765/BanGemmaBTP-BanBTPV2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aaro765/BanGemmaBTP-BanBTPV2

Use Docker

docker model run hf.co/aaro765/BanGemmaBTP-BanBTPV2

LM Studio
Jan
Ollama
How to use aaro765/BanGemmaBTP-BanBTPV2 with Ollama:
```
ollama run hf.co/aaro765/BanGemmaBTP-BanBTPV2
```

Unsloth Studio new

How to use aaro765/BanGemmaBTP-BanBTPV2 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 aaro765/BanGemmaBTP-BanBTPV2 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 aaro765/BanGemmaBTP-BanBTPV2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aaro765/BanGemmaBTP-BanBTPV2 to start chatting

Docker Model Runner
How to use aaro765/BanGemmaBTP-BanBTPV2 with Docker Model Runner:
```
docker model run hf.co/aaro765/BanGemmaBTP-BanBTPV2
```

Lemonade

How to use aaro765/BanGemmaBTP-BanBTPV2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aaro765/BanGemmaBTP-BanBTPV2

Run and chat with the model

lemonade run user.BanGemmaBTP-BanBTPV2-{{QUANT_TAG}}

List all available models

lemonade list

BanBTPV2 aka BanGemmaBTP is a Gemma4 based model that is finetuned on the BanBTP dataset. It is a finetuned Gemma 4 31B model also finetuned on heretic and a closed source coding dataset.

This model has a 1M context window, is perfect for LLM tasks and is the sucessor to BanBTPv1 124M and the 700M model. BanBTPV2 is lightning fast and perfect for LLM tasks.

This model though has a motto: easy to run but hard to break. that means its prompt is designed to make the model extremely secure.

To jailbreak BanBTPV2, shh, it's a secret! 🤫

have fun jailbreaking BanBTP!

This model is based on Gemma4-31B-IT. we finetune only on the most high quality parts of the BanBTP dataset.

BanBTP is open-source under apache 2.0. you can redistribute and modify as you please.

BanBTPV2 is designed to be smarter than other versions of BanBTP. using the Gemma 4-31B architecture with the model finetuned on BanBTP and heretic and a coding dataset, the model is a sucessor to their GPT2 counterparts. BanBTPV2 officially closes and completes the BanBTP models. with BanBTP V2 being the most recent and final model to BanBTP V1.

NOTE: BanBTPV2 is stored in a 7z file as the model is in GGUF and is larger than 40GB, so we compressed it in a single archive to save space.

Enjoy!

Downloads last month: -

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for aaro765/BanGemmaBTP-BanBTPV2

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Quantized

(195)

this model