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
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,24 +1,69 @@
|
|
| 1 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- gguf
|
| 4 |
-
-
|
| 5 |
-
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
-
# BeejX-Gemma2-2B-Hindi-SFT
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
|
|
|
|
| 12 |
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
- For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
|
| 16 |
|
| 17 |
-
|
| 18 |
-
- `gemma-2-2b-it.Q4_K_M.gguf`
|
| 19 |
|
| 20 |
-
##
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
|
|
|
|
|
| 1 |
+
"""---
|
| 2 |
+
language:
|
| 3 |
+
- hi
|
| 4 |
+
- en
|
| 5 |
+
- hinglish
|
| 6 |
tags:
|
| 7 |
+
- agriculture
|
| 8 |
+
- farming
|
| 9 |
+
- india
|
| 10 |
+
- kisan
|
| 11 |
+
- gemma
|
| 12 |
- gguf
|
| 13 |
+
- text-generation-inference
|
| 14 |
+
- on-device
|
| 15 |
+
- android
|
| 16 |
+
base_model: unsloth/gemma-2-2b-it-bnb-4bit
|
| 17 |
+
license: gemma
|
| 18 |
+
pipeline_tag: text-generation
|
| 19 |
+
quantized_by: bf369
|
| 20 |
---
|
| 21 |
|
| 22 |
+
# BeejX-Gemma2-2B-Hindi-SFT (GGUF)
|
| 23 |
+
|
| 24 |
+
**BeejX** is a lightweight, offline-capable AI assistant specifically fine-tuned for **Indian Agriculture** (Bhartiya Krishi).
|
| 25 |
+
It is designed to run on low-end Android smartphones (4GB+ RAM) using the GGUF format, making it accessible to farmers without active internet connections.
|
| 26 |
+
|
| 27 |
+
## Model Details
|
| 28 |
+
- **Base Model:** [Gemma 2 2B Instruct](https://huggingface.co/google/gemma-2-2b-it) (Google)
|
| 29 |
+
- **Fine-tuning:** Supervised Fine-Tuning (SFT) using [Unsloth](https://github.com/unslothai/unsloth) on 1,000+ samples of Indian agriculture Q&A.
|
| 30 |
+
- **Language:** Hindi (Devanagari), Hinglish (Roman Hindi), and English.
|
| 31 |
+
- **Format:** GGUF (Quantized to `Q4_K_M` for best Mobile balance).
|
| 32 |
+
- **File Size:** ~1.5 GB (Fits easily on modern Android phones).
|
| 33 |
+
|
| 34 |
+
## Capabilities
|
| 35 |
+
- **Crop Advice:** Detailed guides for Wheat (Gehu), Rice (Dhaan), Sugarcane (Ganna), Maize (Makka), etc.
|
| 36 |
+
- **Disease Identification:** Describes symptoms and organic/chemical remedies (e.g., Yellow Rust, Termites, Blight).
|
| 37 |
+
- **Localized Knowledge:** Understands Indian seasons (Rabi, Kharif, Zaid) and local fertilizers (DAP, Urea, NPK).
|
| 38 |
+
- **Safety:** Trained to refuse non-agriculture questions to keep the app focused.
|
| 39 |
+
|
| 40 |
+
## How to Run on Android (Flutter)
|
| 41 |
+
This model is optimized for the `llama.cpp` ecosystem.
|
| 42 |
+
|
| 43 |
+
1. **Download:** Get the `unsloth.Q4_K_M.gguf` file from the [Files tab](./tree/main).
|
| 44 |
+
2. **Move to Device:** Place the file in your App's `ApplicationDocumentsDirectory`.
|
| 45 |
+
3. **Flutter Integration:** Use a library like `llama_cpp_dart` or `fllama`.
|
| 46 |
+
4. **Recommended Parameters:**
|
| 47 |
+
- `context_size`: 2048
|
| 48 |
+
- `temperature`: 0.7
|
| 49 |
+
- `system_prompt`:
|
| 50 |
+
```text
|
| 51 |
+
You are BeejX, an expert Indian agriculture assistant.
|
| 52 |
+
Answer in the same language as the user (Hindi/Hinglish).
|
| 53 |
+
Keep answers short, practical, and easy for a farmer to understand.
|
| 54 |
+
```
|
| 55 |
|
| 56 |
+
## How to Run on PC (Ollama)
|
| 57 |
+
You can test this model on your laptop using Ollama before deploying to mobile.
|
| 58 |
|
| 59 |
+
## Limitations & Disclaimer
|
| 60 |
+
AI Advice: This is an AI model. While trained on agricultural data, it can hallucinate. Users should verify chemical dosages with a local Krishi Vigyan Kendra (KVK) expert.
|
|
|
|
| 61 |
|
| 62 |
+
Language: Performance is best in Hindi and Hinglish. Pure regional dialects (like Punjabi/Bhojpuri) may have lower accuracy.
|
|
|
|
| 63 |
|
| 64 |
+
## Credits
|
| 65 |
+
Finetuned by **Bhashkar Fulara** using Unsloth .
|
| 66 |
|
| 67 |
+
```bash
|
| 68 |
+
# Run directly from Hugging Face
|
| 69 |
+
ollama run hf.co/bf369/BeejX-Gemma2-2B-Hindi-SFT
|