Update README.md

README.md

@@ -14,11 +14,31 @@ This model understands **instruction-style prompts** for generating code in mult
 
 ---
 
+##  Requirements (Colab Setup)
+
+If you are running this model on **Google Colab**, you’ll need to:
+
+1. Go to the left sidebar and click the **🔑 (Secrets)** tab.  
+2. Add a new secret with the name:`HF_TOKEN` and set the value to your **Hugging Face token** (from https://huggingface.co/settings/tokens).
+3. Enable **Notebook access** for your token.
+4. Restart the Colab session.
+
+Then log in inside the notebook:
+
+```python
+from huggingface_hub import login
+import os
+
+login(token=os.environ["HF_TOKEN"])
+
+---
+
 ##  How to Use
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+import re
 
 model_id = "key-life/codegen-alpaca-1b"
 
@@ -31,5 +51,26 @@ prompt = "### Instruction:\nWrite a Python function to check if a number is prim
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
 # Generate code
-outputs = model.generate(**inputs, max_new_tokens=128)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=128,
+    temperature=0.2,        # more deterministic
+    top_p=0.9,              # avoids rambling
+    do_sample=True,
+    eos_token_id=tokenizer.eos_token_id,
+    pad_token_id=tokenizer.eos_token_id
+)
+
+# Decode
+decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Extract only code block
+code_block = re.findall(r"```(?:python)?(.*?)```", decoded, re.DOTALL)
+
+if code_block:
+    response = code_block[0].strip()
+else:
+    response = decoded.split("### Response:")[-1].strip()
+
+print(response)
+