Add model card

README.md

@@ -0,0 +1,51 @@
+
+# gemma2b-nirf-lookup-gguf
+
+This is a GGUF conversion of [coderop12/gemma2b-nirf-lookup-2025](https://huggingface.co/coderop12/gemma2b-nirf-lookup-2025).
+
+## Model Details
+- **Original Model**: coderop12/gemma2b-nirf-lookup-2025
+- **Format**: GGUF (F16 precision)
+- **File Size**: ~4.9 GB
+- **Architecture**: Gemma 2B
+- **Specialization**: NIRF (National Institutional Ranking Framework) lookup and ranking queries
+
+## Usage
+
+### With llama.cpp
+```bash
+./llama-cli -m gemma2b-nirf-lookup-gguf.gguf -p "What is the NIRF ranking methodology?"
+```
+
+### With Python (llama-cpp-python)
+```python
+from llama_cpp import Llama
+
+llm = Llama(model_path="gemma2b-nirf-lookup-gguf.gguf")
+response = llm("What are the top NIRF ranked engineering colleges?")
+print(response['choices'][0]['text'])
+```
+
+### With Ollama
+```bash
+# First, create a Modelfile
+echo 'FROM ./gemma2b-nirf-lookup-gguf.gguf' > Modelfile
+ollama create gemma2b-nirf-lookup-gguf -f Modelfile
+ollama run gemma2b-nirf-lookup-gguf "Explain NIRF ranking parameters"
+```
+
+## Model Capabilities
+This model is specifically fine-tuned for:
+- NIRF ranking information and queries
+- Indian higher education institutional data
+- University and college ranking explanations
+- Educational policy and framework questions
+
+## Technical Details
+- **Quantization**: F16 (16-bit floating point)
+- **Context Length**: 2048 tokens
+- **License**: Follow original model license terms
+- **Converted using**: llama.cpp conversion tools
+
+## Original Model License
+Please refer to the original model repository for license information.