Update README.md

README.md

@@ -48,6 +48,10 @@ The training format follows:
 
 ## 🔧 How to Use
 
+### Install dependencies (if not installed):
+```bash
+pip install transformers bitsandbytes
+```
 ### Load model normally:
 
 ``` python
@@ -72,11 +76,11 @@ inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
 with torch.no_grad():
     output = model.generate(
         **inputs,
-        max_new_tokens=3000,      
+        max_new_tokens=3000,
         temperature=0.7,
         top_p=0.9,
         do_sample=True,
-        eos_token_id=tokenizer.convert_tokens_to_ids("</think>")
+        repetition_penalty=1.2,
     )
 
 print(tokenizer.decode(output[0], skip_special_tokens=False))