Update README.md

README.md

@@ -85,22 +85,25 @@ The model was fine-tuned on a combination of the following datasets:
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from huggingface_hub import snapshot_download
 
 device = "cuda"
 
+# Download the model from Hugging Face
+model_dir = snapshot_download("MeowML/E-Model-V2")
+
 # Load the merged fine-tuned model and tokenizer
-model_dir = "E-Model-V2"
 model = AutoModelForCausalLM.from_pretrained(
-    model_dir,
-    torch_dtype=torch.float16,  # Use FP16 for memory efficiency
-    device_map="auto"           # Automatically map to GPU
+   model_dir,
+   torch_dtype=torch.float16,  # Use FP16 for memory efficiency
+   device_map="auto"           # Automatically map to GPU
 )
 tokenizer = AutoTokenizer.from_pretrained(model_dir)
 
 # Ensure EOS token is set correctly
 eos_token = tokenizer("<|im_end|>", add_special_tokens=False)["input_ids"][0]
 if tokenizer.eos_token_id is None:
-    tokenizer.eos_token_id = eos_token
+   tokenizer.eos_token_id = eos_token
 
 # Move model to device (if not already mapped)
 model.to(device)
@@ -113,43 +116,43 @@ print("Merhaba! Size nasıl yardımcı olabilirim? (Çıkmak için 'çık' yazı
 conversation_history = [{"role": "system", "content": system_prompt}]  # Initialize with system prompt
 
 while True:
-    # Get user input
-    user_input = input("Siz: ")
-    
-    # Exit condition
-    if user_input.lower() == "çık":
-        print("Görüşmek üzere!")
-        break
-    
-    # Add user input to conversation history
-    conversation_history.append({"role": "user", "content": user_input})
-    
-    # Tokenize the conversation history
-    encodeds = tokenizer.apply_chat_template(conversation_history, return_tensors="pt")
-    model_inputs = encodeds.to(device)
-    
-    # Generate response
-    generated_ids = model.generate(
-        model_inputs,
-        max_new_tokens=1024,
-        do_sample=True,
-        eos_token_id=eos_token,
-        temperature=0.7,
-        top_p=0.95
-    )
-    
-    # Decode the response
-    generated_text = tokenizer.decode(generated_ids[0][model_inputs.shape[1]:], skip_special_tokens=True)
-    
-    # Add assistant response to history
-    conversation_history.append({"role": "assistant", "content": generated_text})
-    
-    # Print the response
-    print(f"Asistan: {generated_text}")
+   # Get user input
+   user_input = input("Siz: ")
+   
+   # Exit condition
+   if user_input.lower() == "çık":
+       print("Görüşmek üzere!")
+       break
+   
+   # Add user input to conversation history
+   conversation_history.append({"role": "user", "content": user_input})
+   
+   # Tokenize the conversation history
+   encodeds = tokenizer.apply_chat_template(conversation_history, return_tensors="pt")
+   model_inputs = encodeds.to(device)
+   
+   # Generate response
+   generated_ids = model.generate(
+       model_inputs,
+       max_new_tokens=1024,
+       do_sample=True,
+       eos_token_id=eos_token,
+       temperature=0.7,
+       top_p=0.95
+   )
+   
+   # Decode the response
+   generated_text = tokenizer.decode(generated_ids[0][model_inputs.shape[1]:], skip_special_tokens=True)
+   
+   # Add assistant response to history
+   conversation_history.append({"role": "assistant", "content": generated_text})
+   
+   # Print the response
+   print(f"Asistan: {generated_text}")
 
 # Optional: Clear memory when done
 del model
-torch.cuda.empty_cache() 
+torch.cuda.empty_cache()
 ```
 
 ### 9. Ethical Considerations