Update README.md

README.md

@@ -173,37 +173,49 @@ The current model demonstrates a substantial improvement over the previous [Dr.
 
 ### Usage:
 ```python
+import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("sethuiyer/Medichat-Llama3-8B")
-model = AutoModelForCausalLM.from_pretrained("sethuiyer/Medichat-Llama3-8B").to("cuda")
-
-# Function to format and generate response with prompt engineering using a chat template
-def askme(question):
-    sys_message = ''' 
-    You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
-    provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
+class MedicalAssistant:
+    def __init__(self, model_name="sethuiyer/Medichat-Llama3-8B", device="cuda"):
+        self.device = device
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name).to(self.device)
+        self.sys_message = ''' 
+        You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
+        provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
+        '''
+
+    def format_prompt(self, question):
+        messages = [
+            {"role": "system", "content": self.sys_message},
+            {"role": "user", "content": question}
+        ]
+        prompt = self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+        return prompt
+
+    def generate_response(self, question, max_new_tokens=512):
+        prompt = self.format_prompt(question)
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
+        with torch.no_grad():
+            outputs = self.model.generate(**inputs, max_new_tokens=max_new_tokens, use_cache=True)
+        answer = self.tokenizer.batch_decode(outputs, skip_special_tokens=True)[0].strip()
+        return answer
+
+if __name__ == "__main__":
+    assistant = MedicalAssistant()
+    question = '''
+    Symptoms:
+    Dizziness, headache, and nausea.
+
+    What is the differential diagnosis?
     '''
+    response = assistant.generate_response(question)
+    print(response)
 
-    # Create messages structured for the chat template
-    messages = [{"role": "system", "content": sys_message}, {"role": "user", "content": question}]
-
-    # Applying chat template
-    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-    outputs = model.generate(**inputs, max_new_tokens=512, use_cache=True)  # Adjust max_new_tokens for longer responses
-
-    # Extract and return the generated text
-    answer = tokenizer.batch_decode(outputs)[0].strip()
-    return answer
-
-# Example usage
-question = '''
-Symptoms:
-Dizziness, headache and nausea.
-
-What is the differnetial diagnosis?
-'''
-print(askme(question))
 ```
+
+## Ollama
+This model is now also available on Ollama. You can use it by running the command ```ollama run monotykamary/medichat-llama3``` in your 
+terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on 
+a Google Colab backend.