Update app.py

app.py

@@ -1,43 +1,32 @@
 import os
+import torch
 from threading import Thread
 from typing import Iterator
 
 import gradio as gr
 import spaces
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# Konfigurationsparameter
 MAX_MAX_NEW_TOKENS = 100
 DEFAULT_MAX_NEW_TOKENS = 20
-MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "200"))
-
-DESCRIPTION = """\
-# Löwolf Chat
-
-"""
-
-LICENSE = """
-<p/>
----
-"""
-
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
-
+MAX_INPUT_TOKEN_LENGTH = 200  # Anpassung auf 400 Tokens
 
+# Modell und Tokenizer laden
+model_id = "Loewolf/GPT_1"
 if torch.cuda.is_available():
-    model_id = "Loewolf/GPT_1"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
-    tokenizer.use_default_system_prompt = False
-
+else:
+    raise EnvironmentError("CUDA ist nicht verfügbar. Dieses Skript benötigt eine GPU.")
 
+# Gradio Chat Interface Funktion
 @spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
     system_prompt: str,
-    max_new_tokens: int = 50,
+    max_new_tokens: int = DEFAULT_MAX_NEW_TOKENS,
     temperature: float = 0.6,
     top_p: float = 0.9,
     top_k: int = 50,
@@ -50,90 +39,42 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = tokenizer(conversation, return_tensors="pt", truncation=True, max_length=MAX_INPUT_TOKEN_LENGTH)
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
+        input_ids=input_ids,
+        max_new_tokens=min(max_new_tokens, MAX_MAX_NEW_TOKENS),
+        temperature=temperature,
         top_p=top_p,
         top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
         repetition_penalty=repetition_penalty,
+        pad_token_id=tokenizer.eos_token_id
     )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
 
+    outputs = model.generate(**generate_kwargs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-chat_interface = gr.ChatInterface(
+# Gradio Interface
+chat_interface = gr.Interface(
     fn=generate,
-    additional_inputs=[
-        gr.Textbox(label="System prompt", lines=6),
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=1.0,
-            step=0.1,
-            value=0.6,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
-    stop_btn=None,
-    examples=[
-        ["Hello there! How are you doing?"],
-        ["Can you explain briefly to me what is the Python programming language?"],
-        ["Explain the plot of Cinderella in a sentence."],
-        ["How many hours does it take a man to eat a Helicopter?"],
-        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+    inputs=[
+        gr.Textbox(label="Message"),
+        gr.JSON(label="Chat History"),
+        gr.Textbox(label="System Prompt", lines=2),
+        gr.Slider(label="Max new tokens", minimum=1, maximum=MAX_MAX_NEW_TOKENS, step=1, value=DEFAULT_MAX_NEW_TOKENS),
+        gr.Slider(label="Temperature", minimum=0.1, maximum=1.0, step=0.1, value=0.6),
+        gr.Slider(label="Top-p (nucleus sampling)", minimum=0.05, maximum=1.0, step=0.05, value=0.9),
+        gr.Slider(label="Top-k", minimum=1, maximum=1000, step=1, value=50),
+        gr.Slider(label="Repetition penalty", minimum=1.0, maximum=2.0, step=0.05, value=1.2)
     ],
+    outputs="text",
+    live=True
 )
 
-with gr.Blocks(css="style.css") as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    chat_interface.render()
-    gr.Markdown(LICENSE)
-
+# Starten des Gradio-Servers
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    chat_interface.launch()
+