Update app.py

app.py

@@ -1,16 +1,96 @@
 import gradio as gr
 import spaces
 import torch
+from threading import Thread
 
-zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 
-@spaces.GPU
-def greet(n):
-    print(zero.device) # <-- 'cuda:0' 🤗
-    return f"Hello {zero + n} Tensor"
+TITLE = "<h1><center>LLaMA Board: A One-stop Web UI for Getting Started with LLaMA Factory</center></h1>"
 
+DESCRIPTION = "<h3><center>Visit <a href='' target='_blank'>LLaMA Factory</a> for details.</center></h3>"
 
-demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
-demo.launch()
+CSS = r"""
+.duplicate-button {
+  margin: auto !important;
+  color: white !important;
+  background: black !important;
+  border-radius: 100vh !important;
+}
+"""
+
+
+tokenizer = AutoTokenizer.from_pretrained("shenzhi-wang/Llama3-8B-Chinese-Chat")
+model = AutoModelForCausalLM.from_pretrained("shenzhi-wang/Llama3-8B-Chinese-Chat", device_map="auto")
+
+
+@spaces.GPU(duration=120)
+def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int):
+    conversation = []
+    for prompt, answer in history:
+        conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
+
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").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,
+        temperature=temperature,
+        do_sample=True,
+    )
+    if temperature == 0:
+        generate_kwargs["do_sample"] = False
+
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    output = ""
+    for new_token in streamer:
+        outputs += new_token
+        yield output
+
+
+with gr.Blocks(fill_height=True, css=CSS) as demo:
+    gr.HTML(TITLE)
+    gr.HTML(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_classes="duplicate-button")
+
+    gr.ChatInterface(
+        fn=stream_chat,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(
+                minimum=0,
+                maximum=1,
+                step=0.1,
+                value=0.95,
+                label="Temperature",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=128,
+                maximum=4096,
+                step=1,
+                value=512,
+                label="Max new tokens",
+                render=False,
+            ),
+        ],
+        examples=[
+            ['How to setup a human base on Mars? Give short answer.'],
+            ['Explain theory of relativity to me like I’m 8 years old.'],
+            ['What is 9,000 * 9,000?'],
+            ['Write a pun-filled happy birthday message to my friend Alex.'],
+            ['Justify why a penguin might make a good king of the jungle.']
+        ],
+        cache_examples=False,
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()