Update README with proper YAML metadata

README.md

@@ -1,6 +1,23 @@
 ---
-base_model:
-- BioMistral/BioMistral-7B
+license: apache-2.0
+base_model: BioMistral/BioMistral-7B
+tags:
+- medical
+- biomedical
+- healthcare
+- question-answering
+- lora
+- peft
+- medquad
+- biomistral
+- instruction-tuning
+language:
+- en
+datasets:
+- jpmiller/medquad
+library_name: peft
+pipeline_tag: text-generation
+model_type: mistral
 ---
 
 # BioMistral-7B LoRA Fine-tuned on MedQuAD
@@ -74,51 +91,7 @@ pip install transformers peft torch accelerate bitsandbytes
 
 ## Usage
 
-### Option 1: Using the Full Fine-tuned Model
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-
-# Load the fine-tuned model
-model_name = "ayuwal12/biomistral-7b-finetuned"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    device_map="auto",
-    torch_dtype=torch.float16
-)
-
-def generate_medical_response(question, context="", max_length=256):
-    # Format the prompt for medical Q&A
-    if context.strip():
-        prompt = f"### Instruction:\\n{question}\\n\\n### Input:\\n{context}\\n\\n### Response:\\n"
-    else:
-        prompt = f"### Instruction:\\n{question}\\n\\n### Response:\\n"
-    
-    # Tokenize and generate
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    
-    with torch.no_grad():
-        outputs = model.generate(
-            **inputs,
-            max_new_tokens=max_length,
-            temperature=0.7,
-            do_sample=True,
-            pad_token_id=tokenizer.eos_token_id,
-            eos_token_id=tokenizer.eos_token_id
-        )
-    
-    # Decode and extract response
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response.split("### Response:\\n")[-1].strip()
-
-# Example usage
-response = generate_medical_response("What is diabetes and what are its main types?")
-print(response)
-```
-
-### Option 2: Using LoRA Adapters (Recommended)
+### Using LoRA Adapters (Recommended)
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -144,9 +117,9 @@ if tokenizer.pad_token is None:
 
 def generate_medical_response(question, context="", max_length=256):
     if context.strip():
-        prompt = f"### Instruction:\\n{question}\\n\\n### Input:\\n{context}\\n\\n### Response:\\n"
+        prompt = f"### Instruction:\n{question}\n\n### Input:\n{context}\n\n### Response:\n"
     else:
-        prompt = f"### Instruction:\\n{question}\\n\\n### Response:\\n"
+        prompt = f"### Instruction:\n{question}\n\n### Response:\n"
     
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     
@@ -160,7 +133,7 @@ def generate_medical_response(question, context="", max_length=256):
         )
     
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response.split("### Response:\\n")[-1].strip()
+    return response.split("### Response:\n")[-1].strip()
 
 # Example usage
 response = generate_medical_response("What are the symptoms of hypertension?")
@@ -258,7 +231,7 @@ If you use this model, please cite:
   title={BioMistral-7B LoRA Fine-tuned on MedQuAD},
   author={Ayuwal},
   year={2024},
-  howpublished={https://huggingface.co/ayuwal12/biomistral-7b-finetuned},
+  howpublished={https://huggingface.co/ayuwal12/biomistral-7b-lora-adapters},
 }
 ```
 
@@ -276,4 +249,4 @@ For questions or issues, please open an issue on the model repository.
 
 ---
 
-*This model was trained on the MedQuAD dataset and is intended for educational and research purposes in the medical domain. Always consult healthcare professionals for medical advice.*
+*This model was trained on the MedQuAD dataset and is intended for educational and research purposes in the medical domain. Always consult healthcare professionals for medical advice.*