Update README with both LoRA and merged model usage options

README.md

@@ -22,11 +22,33 @@ The model was trained on curated SCI-related content including:
 
 ## Usage
 
+This repository contains both the LoRA adapter and the full merged model. Choose the option that works best for you:
+
+### Option 1: Use the Full Merged Model (Recommended)
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("your-username/sci-assistant-7b")
-tokenizer = AutoTokenizer.from_pretrained("your-username/sci-assistant-7b")
+model = AutoModelForCausalLM.from_pretrained("basiphobe/sci-assistant")
+tokenizer = AutoTokenizer.from_pretrained("basiphobe/sci-assistant")
+
+# Example usage
+prompt = "What are the signs of autonomic dysreflexia?"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=200)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+### Option 2: Use the LoRA Adapter (Smaller Download)
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B")
+tokenizer = AutoTokenizer.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "basiphobe/sci-assistant")
 
 # Example usage
 prompt = "What are the signs of autonomic dysreflexia?"
@@ -48,6 +70,12 @@ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 - Not a replacement for professional medical care
 - May not reflect the most recent medical developments
 
+## Files in this Repository
+
+- **Full Merged Model**: Ready-to-use model files (`model-*.safetensors`, `config.json`, etc.)
+- **LoRA Adapter**: Smaller adapter files (`adapter_model.safetensors`, `adapter_config.json`)
+- **Tokenizer**: Shared tokenizer files for both options
+
 ## Technical Details
 
 - **Base Model**: teknium/OpenHermes-2.5-Mistral-7B