Update README.md

README.md

@@ -38,14 +38,13 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 model_path = "RajuKandasamy/ponniyinselvan_1.4b_alpha"
 device = "cuda" if torch.cuda.is_available() else "cpu" 
 model = AutoModelForCausalLM.from_pretrained(model_path, load_in_8bit=False).to(device)
-
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 model.eval()
 
 prompt="""வந்தியத்தேவன்"""
 input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
-attention_mask = torch.ones_like(input_ids).to(model.device) # set attention mask to 1 for all input tokens
+attention_mask = torch.ones_like(input_ids).to(model.device)
 print("Thinking ...\n   ")
 with torch.no_grad():
     output = model.generate(input_ids=input_ids, attention_mask=attention_mask, max_length=256, early_stopping=False, temperature=0.9, top_p=0.9,top_k=500, do_sample=True,output_scores=True,  pad_token_id=tokenizer.eos_token_id, repetition_penalty=1.2,eos_token_id=tokenizer.eos_token_id)