Update README.md

README.md

@@ -28,8 +28,8 @@ It may produce some harmful output.
 
 Examples:
 
-| Prompt | BrtGPT-1-Pre | BrtGPT-1-Pre-Code |
-| :------------: | :------------: | :------------: |
+| Prompt | BrtGPT-1-Pre |
+| :------------: | :------------: |
 | "Write me a code that prints "Hello World". | "Here's a code that prints "Hello World" in a list of words:```for i in range(1, 2, 3, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5," |
 | "Write me a code that generates random number."| Code: |
 
@@ -67,3 +67,100 @@ def generate_random_number(num):
     # Create a new
 ```
 
+
+## How to use?
+
+You can run this code to use:
+
+```
+import torch
+from transformers import PreTrainedTokenizerFast, GPT2LMHeadModel
+
+def extract_response_between_tokens(text: str) -> str:
+
+    start_token = "<|im_start|>assistant<|im_sep|>"
+    end_token = "<|im_end|>"
+    try:
+        start_idx = text.index(start_token) + len(start_token)
+        end_idx = text.index(end_token, start_idx)
+        return text[start_idx:end_idx]
+    except ValueError:
+        # Tokenlar bulunamazsa orijinal metni döndür
+        return text
+
+if __name__ == "__main__":
+    model_name_or_path = "Bertug1911/BrtGPT-1-Pre"
+
+    tokenizer = PreTrainedTokenizerFast.from_pretrained(model_name_or_path)
+    model = GPT2LMHeadModel.from_pretrained(model_name_or_path)
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    model.eval()
+
+    user_input = input("Enter something to ask model: ")
+
+
+    messages = [{"role": "user", "content": user_input}]
+
+
+    formatted_prompt = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+
+    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(device)
+    generated = inputs["input_ids"]
+
+    # Generate config
+    max_new_tokens = 128
+    do_sample = True
+    top_k = 40
+    temperature = 0.8
+
+    im_end_token_id = tokenizer.convert_tokens_to_ids("<|im_end|>")
+
+    with torch.no_grad():
+        for i in range(max_new_tokens):
+            outputs = model(generated)
+            logits = outputs.logits[:, -1, :]
+            logits = logits / temperature
+
+            if top_k > 0:
+                top_k_values, top_k_indices = torch.topk(logits, top_k)
+                logits_filtered = torch.full_like(logits, float('-inf'))
+                logits_filtered.scatter_(1, top_k_indices, top_k_values)
+                logits = logits_filtered
+
+            probs = torch.softmax(logits, dim=-1)
+
+            if do_sample:
+                next_token = torch.multinomial(probs, num_samples=1)
+            else:
+                next_token = torch.argmax(probs, dim=-1, keepdim=True)
+
+            generated = torch.cat([generated, next_token], dim=1)
+
+            if next_token.item() == im_end_token_id:
+                break
+
+
+
+    output = tokenizer.decode(generated[0], skip_special_tokens=False)
+
+    # Special token conversions
+    no_spaces = output.replace(" ", "")
+    step2 = no_spaces.replace("Ġ", " ")
+    formatted_output = step2.replace("Ċ", "\n")
+
+    if not formatted_output.strip().endswith("<|im_end|>"):
+        formatted_output += "<|im_end|>"
+
+
+    assistant_response = extract_response_between_tokens(formatted_output)
+    print("\nModel output:\n", assistant_response)
+
+```
+