Text Generation
Safetensors
GGUF
Hindi
English
gemma2
agriculture
farming
india
gemma
text-generation-inference
conversational
unsloth
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
- llama.cpp
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 Desktop
- 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
|
Download README.md from bf369/BeejX-Gemma2-2B-Hindi-SFT: direct link, hf CLI and curl.
- Browser
- Download file 1.55 kB
-
https://huggingface.co/bf369/BeejX-Gemma2-2B-Hindi-SFT/resolve/main/README.md
- Command line
-
hf download hf://bf369/BeejX-Gemma2-2B-Hindi-SFT/README.md
-
curl -L -o README.md https://huggingface.co/bf369/BeejX-Gemma2-2B-Hindi-SFT/resolve/main/README.md
1.55 kB
| language: | |
| - hi | |
| - en | |
| tags: | |
| - agriculture | |
| - farming | |
| - india | |
| - gemma | |
| - gguf | |
| - text-generation-inference | |
| - conversational | |
| - unsloth | |
| base_model: unsloth/gemma-2-2b-it-bnb-4bit | |
| license: gemma | |
| pipeline_tag: text-generation | |
| # 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](https://huggingface.co/google/gemma-2-2b-it) | |
| - **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`. | |
| 1. **Download:** Get the `unsloth.Q4_K_M.gguf` file from the [Files tab](./tree/main). | |
| 2. **Load:** Use a context size of `2048`. | |
| 3. **Recommended System Prompt:** | |
| ```text | |
| 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. """ |