Update README.md

README.md

@@ -46,25 +46,35 @@ from transformers import AutoTokenizer
 import transformers
 import torch
 
+# Load tokenizer and model
 model = "Kumar955/Hemanth-llm"
+tokenizer = AutoTokenizer.from_pretrained(model)
+
+# Define the messages from the conversation
 messages = [{"role": "user", "content": "What is a large language model?"}]
 
-tokenizer = AutoTokenizer.from_pretrained(model)
+# Define the chat template for formatting the conversation
+chat_template = """<s><|user|>{{ user_message }}<|assistant|>"""
 
-# Define a chat template
-chat_template = """<s><|user|>{{ user_message }}<|assistant|>""" 
+# Extract the user message content
+user_message = messages[0]["content"]
 
-# Use the chat template in apply_chat_template
-prompt = tokenizer.apply_chat_template(messages, chat_template=chat_template, tokenize=False, add_generation_prompt=True) 
+# Format the prompt using the chat template
+prompt = chat_template.replace("{{ user_message }}", user_message)
 
-pipeline = transformers.pipeline(
+# Load the pipeline with the specified model
+pipeline = pipeline(
     "text-generation",
     model=model,
     torch_dtype=torch.float16,
     device_map="auto",
 )
 
+# Generate output with the model
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+
+# Print the generated response
 print(outputs[0]["generated_text"])
 
+
 ```