Update README.md

README.md

@@ -69,98 +69,36 @@ def generate_random_number(num):
 
 
 ## How to use?
-NOTE: Model ***DON'T*** supports "Auto-model". (If you use with auto model, it generates random outputs!!!)
-You can run this code to use:
+NOTE: Model ***Supports*** Auto-model library now!
+You can run this code to use (Auto-model/Hugging Face transformers):
 
 ```
-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)
+from transformers import pipeline
+
+# Pipeline
+pipe = pipeline(
+    "text-generation",
+    model="Bertug1911/BrtGPT-1-Pre",
+    trust_remote_code=True,
+    top_k=40,              # örnek bir top_k değeri
+    temperature=0.8,       # örnek bir temperature değeri
+    max_new_tokens=50      # maksimum üretilecek yeni token sayısı
+)
+
+# Messages
+messages = [
+    {"role": "user", "content": "What is the capital of France?"},
+]
+
+# Take out
+output = pipe(messages)
+
+# Only write asistant's (Model output) answer
+assistant_response = output[0]["generated_text"][-1]["content"].strip()
+# Special token conversions
+formatted_out = assistant_response.replace(" ", "").replace("Ġ", " ").replace("Ċ", "\n")
+
+print(formatted_out)
 
 ```
 ## Evulation