Update app.py

app.py

@@ -6,9 +6,14 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-
 DESCRIPTION = """\
-# Backend for Sergidev
+# Qwen 0.5B Text Completion
+
+This is a demo of [`Qwen/Qwen2-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct), a lightweight language model fine-tuned for instruction following.
+
+This space allows you to input text and have the AI complete it. Simply type your text in the input box, click "Complete", and watch as the AI generates a continuation of your text.
+
+You can adjust various parameters such as temperature and top-p sampling to control the generation process.
 """
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -26,31 +31,19 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 model.eval()
 
-
 @spaces.GPU(duration=90)
 def generate(
     message: str,
-    chat_history: list[tuple[str, str]],
     max_new_tokens: int = 1024,
     temperature: float = 0.6,
     top_p: float = 0.9,
     top_k: int = 50,
     repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
-    conversation = []
-    for user, assistant in chat_history:
-        conversation.extend(
-            [
-                {"role": "user", "content": user},
-                {"role": "assistant", "content": assistant},
-            ]
-        )
-    conversation.append({"role": "user", "content": message})
-
-    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt")
+    input_ids = tokenizer.encode(message, 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.")
+        gr.Warning(f"Trimmed input as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
     streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
@@ -71,63 +64,86 @@ def generate(
     outputs = []
     for text in streamer:
         outputs.append(text)
-        yield "".join(outputs)
-
-
-chat_interface = gr.ChatInterface(
-    fn=generate,
-    additional_inputs=[
-        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=4.0,
-            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'"],
-    ],
-    cache_examples=False,
-)
+        yield message + "".join(outputs)
 
 with gr.Blocks(css="style.css", fill_height=True) as demo:
     gr.Markdown(DESCRIPTION)
     gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    chat_interface.render()
+
+    with gr.Row():
+        with gr.Column(scale=4):
+            input_box = gr.Textbox(
+                label="Enter your text",
+                placeholder="Type your message here...",
+                lines=5
+            )
+            output_box = gr.Textbox(
+                label="Completed text",
+                lines=10,
+                interactive=False
+            )
+        with gr.Column(scale=1):
+            max_new_tokens = gr.Slider(
+                label="Max new tokens",
+                minimum=1,
+                maximum=MAX_MAX_NEW_TOKENS,
+                step=1,
+                value=DEFAULT_MAX_NEW_TOKENS,
+            )
+            temperature = gr.Slider(
+                label="Temperature",
+                minimum=0.1,
+                maximum=4.0,
+                step=0.1,
+                value=0.6,
+            )
+            top_p = gr.Slider(
+                label="Top-p (nucleus sampling)",
+                minimum=0.05,
+                maximum=1.0,
+                step=0.05,
+                value=0.9,
+            )
+            top_k = gr.Slider(
+                label="Top-k",
+                minimum=1,
+                maximum=1000,
+                step=1,
+                value=50,
+            )
+            repetition_penalty = gr.Slider(
+                label="Repetition penalty",
+                minimum=1.0,
+                maximum=2.0,
+                step=0.05,
+                value=1.2,
+            )
+
+    complete_btn = gr.Button("Complete")
+
+    complete_btn.click(
+        fn=generate,
+        inputs=[
+            input_box,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+            repetition_penalty
+        ],
+        outputs=output_box
+    )
+
+    gr.Examples(
+        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=input_box
+    )
 
 if __name__ == "__main__":
     demo.queue(max_size=20).launch()