Update README.md

README.md

@@ -32,23 +32,20 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch 
  
 # Load the model and tokenizer 
-model_path = "microsoft/UserLM-8b"  
+model_path = "microsoft/userlm-8b"  
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) 
-model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).to("cuda") 
+model = AutoModelForCausalLM.from_pretrained(model_path,  trust_remote_code=True).to("cuda") 
  
 # Create a conversation 
 messages = [{"role": "system", "content": "You are a user who wants to implement a special type of sequence. The sequence sums up the two previous numbers in the sequence and adds 1 to the result. The first two numbers in the sequence are 1 and 1."}] 
 inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda") 
 
-# Example 1: Generate response
-outputs = model.generate(inputs, max_new_tokens=100, do_sample=True, temperature=1.0) 
-response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True) 
-print(response) # This can output: “Create a sequence that always starts at 1, 1, and then sums the two previous numbers in the sequence, adds 1 to the result.” 
-
-# Example 2: Generate response while ignoring the <|endconversation|> token
+end_token = "<|eot_id|>"
+end_token_id = tokenizer.encode(end_token, add_special_tokens=False)
 
 end_conv_token = "<|endconversation|>"
 end_conv_token_id = tokenizer.encode(end_conv_token, add_special_tokens=False)
+
 outputs = model.generate(
     input_ids=inputs,
     do_sample=True,