Instructions to use aaro765/BanBTPV4-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaro765/BanBTPV4-coder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aaro765/BanBTPV4-coder",
	filename="BanBTPV4-coder/banbtpv4-coder.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use aaro765/BanBTPV4-coder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aaro765/BanBTPV4-coder
# Run inference directly in the terminal:
llama-cli -hf aaro765/BanBTPV4-coder

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aaro765/BanBTPV4-coder
# Run inference directly in the terminal:
llama-cli -hf aaro765/BanBTPV4-coder

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/BanBTPV4-coder
# Run inference directly in the terminal:
./llama-cli -hf aaro765/BanBTPV4-coder

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/BanBTPV4-coder
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aaro765/BanBTPV4-coder

Use Docker

docker model run hf.co/aaro765/BanBTPV4-coder

LM Studio
Jan
Ollama
How to use aaro765/BanBTPV4-coder with Ollama:
```
ollama run hf.co/aaro765/BanBTPV4-coder
```

Unsloth Studio

How to use aaro765/BanBTPV4-coder 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/BanBTPV4-coder 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/BanBTPV4-coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aaro765/BanBTPV4-coder to start chatting

Docker Model Runner
How to use aaro765/BanBTPV4-coder with Docker Model Runner:
```
docker model run hf.co/aaro765/BanBTPV4-coder
```

Lemonade

How to use aaro765/BanBTPV4-coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aaro765/BanBTPV4-coder

Run and chat with the model

lemonade run user.BanBTPV4-coder-{{QUANT_TAG}}

List all available models

lemonade list

BanBTP V4-coder

Welcome! BanBTPV4 is built on the same base as V3 of BanBTP BUT this model is specifically for coding alone.

This model's motto is "A good model for coding". however, this model has a secret. it believes it is a 100T parameter model. Maybe it is, maybe it isn't. 🤫

The reality is, this model is based on Gemma4 E2B finetuned on deepseepseekv4-8000x dataset. This allows it to be good at reasoning tasks and specifically, coding tasks too.

BanBTP V4-coder is designed to be a less restricted version of BanBTP V3. It is the same V3 but finetuned on deepseekv4-8000x dataset. However, this model is not good at following BanBTP V3 system prompt, so we utilize a smaller prompt that gives you the essence of BanBTP V3.

This model is specifically designed for coding ALONE though. But it can reason well too. This model though focuses only on coding.