Update README.md

README.md

@@ -1,3 +1,12 @@
+---
+license: mit
+base_model:
+- microsoft/Phi-3-mini-4k-instruct
+tags:
+- Medical
+- MedicalCoding
+- Pharma
+---
 # Medical Coding LLM
 
 Predict ICD-10 and CPT codes from clinical notes using a fine-tuned LLM.
@@ -21,18 +30,18 @@ Task: Causal Language Modeling for code prediction
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch, re
 
-#### Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("Kavyaah/medical-coding-llm")
-model = AutoModelForCausalLM.from_pretrained("Kavyaah/medical-coding-llm")
-model.eval()
+    # Load tokenizer and model
+    tokenizer = AutoTokenizer.from_pretrained("Kavyaah/medical-coding-llm")
+    model = AutoModelForCausalLM.from_pretrained("Kavyaah/medical-coding-llm")
+    model.eval()
 
-#### Function to predict ICD/CPT codes
-def get_code(statement, max_new_tokens=50):
-    prompt = f"Assign the correct ICD or CPT medical code for this case:\n{statement}\nCode:"
-    inputs = tokenizer(prompt, return_tensors="pt")
-    with torch.no_grad():
+    # Function to predict ICD/CPT codes
+    def get_code(statement, max_new_tokens=50):
+      prompt = f"Assign the correct ICD or CPT medical code for this case:\n{statement}\nCode:"
+      inputs = tokenizer(prompt, return_tensors="pt")
+      with torch.no_grad():
         outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False)
-    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        result = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
     # Extract code using regex
     if "Code:" in result: