Update README.md

README.md

@@ -82,7 +82,7 @@ model = AutoModelForCausalLM.from_pretrained("mkurman/llama-3.2-MEDIT-3B-o1")
 prompt = [{'role': 'user', 'content': 'Write a short instagram post about hypertension in children. Finish with 3 hashtags'}]
 input_ids = tokenizer(tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True) + '<Thought>\n\n', return_tensors='pt')
 
-# 4. Generate response with stop sequences (if your generation method supports them)
+# 3. Generate response with stop sequences (if your generation method supports them)
 #    If your method doesn't support stop sequences directly, 
 #    you can manually slice the model's output at '</Output>'.
 output = model.generate(
@@ -95,7 +95,7 @@ output = model.generate(
     # stop=["</Output>"]
 )
 
-# 5. Decode the output
+# 4. Decode the output
 decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
 print(decoded_output)
 ```
@@ -138,7 +138,7 @@ You would display the `<Output>` portion as the final user-facing answer.
 
 ## License and Citation
 
-Please refer to the base model’s **Llama 3.2 license from Meta** and any additional licenses from MedIT Solutions. If you use this model in your work, please cite:
+Please refer to the base model’s [Llama 3.2 Community License Agreement](LICENSE.txt) and any additional licenses from MedIT Solutions. If you use this model in your work, please cite:
 
 ```
 @misc{mkurman2025llama3medit3bo1,