Update app.py

app.py

@@ -1,64 +1,48 @@
 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
-"""
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Ładowanie polskiego modelu
+model_name = "allegro/herbert-base-cased"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def generate_response(prompt):
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs,
+        max_length=150,
+        num_return_sequences=1,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.95,
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+def chat(message, history):
+    # Formatowanie historii rozmowy
+    formatted_history = ""
+    if history:
+        for human, ai in history:
+            formatted_history += f"Użytkownik: {human}\nAI: {ai}\n"
+    
+    # Tworzenie promptu
+    prompt = f"{formatted_history}Użytkownik: {message}\nAI:"
+    
+    # Generowanie odpowiedzi
+    response = generate_response(prompt)
+    
+    # Usuwanie powtórzeń promptu z odpowiedzi
+    clean_response = response.replace(prompt, "").strip()
+    return clean_response
+
+# Tworzenie interfejsu
 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)",
-        ),
-    ],
+    fn=chat,
+    title="Polski ChatAI",
+    description="Rozmawiaj ze mną po polsku!",
+    examples=["Cześć, jak się masz?", "Opowiedz mi o Warszawie", "Co to jest sztuczna inteligencja?"],
+    theme="soft"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()