Update README.md

README.md

@@ -87,28 +87,68 @@ This model can be used **directly** without any LoRA adapter.
 ### Example (Transformers)
 
 ```python
+!pip uninstall -y transformers peft accelerate torch safetensors numpy
+!pip install numpy==1.26.4
+!pip install torch==2.2.2
+!pip install transformers==4.41.2
+!pip install peft==0.11.1
+!pip install accelerate==0.30.1
+!pip install safetensors==0.4.3
+
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "souvik18/Roy"
+# -----------------------------
+# CONFIG
+# -----------------------------
+MODEL_ID = "souvik18/Roy"
+DTYPE = torch.float16   # use float16 for GPU
+
+# -----------------------------
+# LOAD TOKENIZER & MODEL
+# -----------------------------
+print("🔹 Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+tokenizer.pad_token = tokenizer.eos_token
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+print("🔹 Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.float16,
+    MODEL_ID,
+    torch_dtype=DTYPE,
     device_map="auto"
 )
-
-prompt = "[INST] Explain Newton's laws in simple words [/INST]"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-
-with torch.no_grad():
-    output = model.generate(
-        **inputs,
-        max_new_tokens=200,
-        temperature=0.7,
-        top_p=0.9,
-        do_sample=True
-    )
-
-print(tokenizer.decode(output[0], skip_special_tokens=True))
+model.eval()
+
+print("\n✅ Model loaded successfully")
+print("Type 'exit' or 'quit' to stop\n")
+
+# -----------------------------
+# CHAT LOOP
+# -----------------------------
+while True:
+    user_input = input("🧑 You: ").strip()
+
+    if user_input.lower() in ["exit", "quit"]:
+        print("👋 Bye!")
+        break
+
+    prompt = f"[INST] {user_input} [/INST]"
+
+    inputs = tokenizer(
+        prompt,
+        return_tensors="pt"
+    ).to(model.device)
+
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True,
+            repetition_penalty=1.1,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(f"\n Roy: {response}\n")