Update app.py

app.py

@@ -1,70 +1,63 @@
+import torch
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
 
+BASE_MODEL = "google/gemma-3-270m-it"
+LORA_MODEL = "loboGOAT/DogeAI-v1.0-instruct"  # seu LoRA
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
-    messages = [{"role": "system", "content": system_message}]
+print("🔄 Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
 
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+print("🔄 Loading base model...")
+model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float16 if device == "cuda" else torch.float32,
+    device_map="auto"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+print("🔄 Applying LoRA...")
+model = PeftModel.from_pretrained(model, LORA_MODEL)
+model.eval()
+
+def chat(user_input):
+    prompt = (
+        "<bos>\n"
+        "<start_of_turn>user\n"
+        f"{user_input}\n"
+        "<start_of_turn>model\n"
+    )
+
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.1,
+            eos_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.pad_token_id
+        )
+
+    text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    if "<start_of_turn>model" in text:
+        return text.split("<start_of_turn>model")[-1].strip()
+
+    return text.strip()
+
+demo = gr.Interface(
+    fn=chat,
+    inputs=gr.Textbox(lines=4, placeholder="Talk to DogeAI 🐕"),
+    outputs="text",
+    title="DogeAI v1.0",
+    description="LoRA fine-tuned Gemma-3-270M-it • Created by Arthur"
+)
 
+demo.launch()
 
-if __name__ == "__main__":
-    demo.launch()