Update README.md

README.md

@@ -48,12 +48,11 @@ Fine-tuned for insurance-related queries and conversations.
 - **Quantized Model:** Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B-GGUF
 - **Model Architecture:** Llama
 - **Quantization:** 8-bit (Q8_0), 5-bit (Q5_K_M), 4-bit (Q4_K_M), 16-bit
+- **Finetuned Dataset**: InsuranceQA
 - **Developer:** Raj Maharajwala
 - **License:** llama3
 - **Language:** English
-
-## Finetuned Dataset:
-- **InsuranceQA**
+- 
 
 ## Setup Instructions
 
@@ -79,6 +78,11 @@ export FORCE_CMAKE=1
 CMAKE_ARGS="-DGGML_METAL=on" pip install --upgrade --force-reinstall llama-cpp-python==0.3.2 --no-cache-dir
 ```
 
+#### For Windows Users (CPU Support)
+```bash
+pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+```
+
 ### Dependencies
 
 Then install dependencies (inference_requirements.txt) attached under `Files and Versions`: