Update app.py

app.py

@@ -1,63 +1,75 @@
+from transformers import (AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig)
+from peft import PeftModel
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    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,
-    ):
-        token = message.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
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
+
+# Memuat model
+base_model = AutoModelForCausalLM.from_pretrained(
+    "BioMistral/BioMistral-7B",
+    load_in_8bit=True,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(base_model, "sayyid14/BioMistralCancer5epoch")
+
+generation_config = GenerationConfig(
+    do_sample=False,
+    num_beams=4,
+    repetition_penalty=1.15,
 )
 
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("BioMistral/BioMistral-7B", trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+
+# Fungsi respons
+def chatbot_response(user_input):
+    PROMPT = f"""Below is a question about cancer. Please answer this question correctly. If you don't know the answer just say that you don't know and don't share false information.
+### Question:
+{user_input}
+### Answer:"""
+
+    inputs = tokenizer(PROMPT, return_tensors="pt")
+    input_ids = inputs["input_ids"]
+
+    print("Generating...")
+    generation_output = model.generate(
+        input_ids=input_ids,
+        generation_config=generation_config,
+        return_dict_in_generate=True,
+        max_new_tokens=100,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=tokenizer.eos_token_id
+    )
+
+    for s in generation_output.sequences:
+        result = tokenizer.decode(s).split("### Answer:")[1]
+
+    return result.strip()
+
+# Membuat antarmuka
+iface = gr.Interface(
+    fn=chatbot_response,
+    inputs=gr.Textbox(placeholder="Type your question...", label="User"),
+    outputs=gr.Textbox(label="Bot"),
+    title="BioMistralCancer",
+    description="Ask anything about Cancer",
+    css="""
+        body {
+            background-size: cover;
+            background-repeat: no-repeat;
+            background-position: center;
+            height: 100vh; 
+            margin: 0;
+        }
+        .gradio-container {
+            background-color: rgba(255, 255, 255, 0.8);
+            border-radius: 10px; 
+            padding: 20px; 
+            backdrop-filter: blur(10px);
+        }
+    """
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Menjalankan aplikasi
+iface.launch(share=True)