Update README.md

README.md

@@ -175,68 +175,7 @@ test_prompt = "Who are you?"
 generated_response = generate_text(model, tokenizer, test_prompt, max_length=100)
 print(f"Generated response:\n{generated_response}")
 
-print("Testing completed.")import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel, PeftConfig
-
-# Set the device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(f"Using device: {device}")
-
-# Load the tokenizer
-tokenizer = AutoTokenizer.from_pretrained("CognitivessAI/cognitivess")
-
-# Load the PEFT configuration
-peft_config = PeftConfig.from_pretrained("CognitivessAI/cognitivess")
-
-# Load the base model
-base_model = AutoModelForCausalLM.from_pretrained(
-    peft_config.base_model_name_or_path,
-    device_map="auto",
-    torch_dtype=torch.float16
-)
-
-# Load the PEFT model
-model = PeftModel.from_pretrained(base_model, "CognitivessAI/cognitivess")
-
-# Move the model to the appropriate device
-model = model.to(device)
-
-# Set the model to evaluation mode
-model.eval()
-
-# Function for text generation using the chat template
-def generate_text(model, tokenizer, input_text, max_length=8192, temperature=0.7, top_p=0.95):
-    messages = [
-        {"role": "user", "content": input_text}
-    ]
-    chat_input = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    inputs = tokenizer(chat_input, return_tensors='pt', padding=True, truncation=True, max_length=8192)
-    input_ids = inputs['input_ids'].to(device)
-    attention_mask = inputs['attention_mask'].to(device)
-    try:
-        generated_text_ids = model.generate(
-            input_ids,
-            attention_mask=attention_mask,
-            max_length=max_length,
-            temperature=temperature,
-            top_p=top_p,
-            do_sample=True,
-            eos_token_id=tokenizer.eos_token_id
-        )
-        generated_text = tokenizer.decode(generated_text_ids[0], skip_special_tokens=True)
-        # Extract the assistant's response
-        response = generated_text.split("GPT4 Correct Assistant")[-1].strip()
-        return response
-    except Exception as e:
-        print(f"Error in text generation: {e}")
-        return "I'm sorry, I encountered an error while generating a response."
-
-# Test the model
-test_prompt = "Who are you?"
-generated_response = generate_text(model, tokenizer, test_prompt, max_length=100)
-print(f"Generated response:\n{generated_response}")
-
+print("Testing completed.")
 
 ```