Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,68 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import spaces
+
+model_name = "baidu/ERNIE-4.5-21B-A3B-Thinking"
+
+# Load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
+
+@spaces.GPU(duration=120)
+def chat(message, history):
+    messages = []
+    for user_msg, assistant_msg in history:
+        if user_msg is not None:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg is not None:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    messages.append({"role": "user", "content": message})
+    
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    model_inputs = tokenizer([text], add_special_tokens=False, return_tensors="pt").to(model.device)
+    
+    with torch.no_grad():
+        generated_ids = model.generate(
+            **model_inputs,
+            max_new_tokens=1024,
+            do_sample=True,
+            temperature=0.7,
+        )
+    
+    output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+    generate_text = tokenizer.decode(output_ids, skip_special_tokens=True)
+    
+    history.append((message, generate_text))
+    return history, ""
+
+with gr.Blocks(title="ERNIE Chat") as demo:
+    gr.Markdown("# ERNIE-4.5-21B-A3B-Thinking Chat App")
+    chatbot = gr.Chatbot(
+        height=500,
+        type="messages",
+        show_copy_button=True,
+        avatar_images=("user_icon.png", "bot_icon.png")  # Optional: add icons if available
+    )
+    msg = gr.Textbox(
+        placeholder="Type your message here...",
+        show_label=False,
+        container=True,
+        scale=7,
+    )
+    with gr.Row():
+        clear_btn = gr.Button("Clear", variant="secondary")
+    
+    msg.submit(chat, [msg, chatbot], [chatbot, msg])
+    clear_btn.click(lambda: ([], ""), None, chatbot, queue=False)
+
+if __name__ == "__main__":
+    demo.launch()