Instructions to use bf369/BeejX-Gemma2-2B-Hindi-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bf369/BeejX-Gemma2-2B-Hindi-SFT with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bf369/BeejX-Gemma2-2B-Hindi-SFT: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 bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bf369/BeejX-Gemma2-2B-Hindi-SFT: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 bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M

Use Docker

docker model run hf.co/bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M

LM Studio
Jan

vLLM

How to use bf369/BeejX-Gemma2-2B-Hindi-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bf369/BeejX-Gemma2-2B-Hindi-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bf369/BeejX-Gemma2-2B-Hindi-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M

Ollama
How to use bf369/BeejX-Gemma2-2B-Hindi-SFT with Ollama:
```
ollama run hf.co/bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
```

Unsloth Studio

How to use bf369/BeejX-Gemma2-2B-Hindi-SFT 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 bf369/BeejX-Gemma2-2B-Hindi-SFT 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 bf369/BeejX-Gemma2-2B-Hindi-SFT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bf369/BeejX-Gemma2-2B-Hindi-SFT to start chatting

Docker Model Runner
How to use bf369/BeejX-Gemma2-2B-Hindi-SFT with Docker Model Runner:
```
docker model run hf.co/bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M
```

Lemonade

How to use bf369/BeejX-Gemma2-2B-Hindi-SFT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bf369/BeejX-Gemma2-2B-Hindi-SFT:Q4_K_M

Run and chat with the model

lemonade run user.BeejX-Gemma2-2B-Hindi-SFT-Q4_K_M

List all available models

lemonade list

Atomic Chat

BeejX-Gemma2-2B-Hindi-SFT

BeejX is a lightweight, offline-capable AI assistant specifically fine-tuned for Indian Agriculture. It is designed to run on low-end Android smartphones (4GB RAM) using the GGUF format.

Model Details

Base Model: Gemma 2 2B Instruct
Fine-tuning: Supervised Fine-Tuning (SFT) on 1,000+ samples of Indian agriculture Q&A.
Language: Hindi (Devanagari), Hinglish, and English.
Format: GGUF (Quantized to Q4_K_M for Mobile).

Capabilities

Crop Advice: Wheat (Gehu), Rice (Dhaan), Sugarcane, etc.
Disease Identification: Describes symptoms and remedies (e.g., Yellow Rust, Termites).
Anti-Hallucination: Trained to refuse non-agriculture questions.
Personality: Helpful, direct, and polite Indian agri-assistant.

How to Run on Android (Flutter)

This model is optimized for mobile deployment using llama.cpp or mediapipe.

Download: Get the unsloth.Q4_K_M.gguf file from the Files tab.
Load: Use a context size of 2048.
Recommended System Prompt:

You are BeejX, an expert Indian agriculture assistant. 
Answer in the same language as the user (Hindi/Hinglish). 
Keep answers short, practical, and easy for a farmer to understand. """

Downloads last month: 47

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

4-bit

Model tree for bf369/BeejX-Gemma2-2B-Hindi-SFT

Base model

unsloth/gemma-2-2b-it-bnb-4bit

Quantized

(47)

this model

Adapters

1 model