Update app.py

app.py

@@ -1,63 +1,63 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 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})
+# Set the device
+device = "cpu"  # replace with your device: "cpu", "cuda", "mps"
+
+# Initialize model and tokenizer
+peft_model_id = "CMLM/ZhongJing-2-1_8b"
+base_model_id = "Qwen/Qwen1.5-1.8B-Chat"
+model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto")
+model.load_adapter(peft_model_id)
+tokenizer = AutoTokenizer.from_pretrained(
+    "CMLM/ZhongJing-2-1_8b",
+    padding_side="right",
+    trust_remote_code=True,
+    pad_token=''
+)
 
-    response = ""
+def get_model_response(question):
+    # Create the prompt without context
+    prompt = f"Question: {question}"
+    messages = [
+        {"role": "system", "content": "You are a helpful TCM medical assistant named 仲景中医大语言模型, created by 医哲未来 of Fudan University."},
+        {"role": "user", "content": prompt}
+    ]
 
-    for message in client.chat_completion(
+    # Prepare the input
+    text = tokenizer.apply_chat_template(
         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
-"""
-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)",
-        ),
-    ],
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+    # Generate the response
+    generated_ids = model.generate(
+        model_inputs.input_ids,
+        max_new_tokens=512
+    )
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+
+    # Decode the response
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return response
+
+# Define a Gradio interface without the context parameter
+def chat_interface(question):
+    response = get_model_response(question)
+    return response
+
+iface = gr.Interface(
+    fn=chat_interface,
+    inputs=["text"],
+    outputs="text",
+    title="仲景GPT-V2-1.8B",
+    description="博极医源，精勤不倦。Unlocking the Wisdom of Traditional Chinese Medicine with AI."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface with sharing enabled
+iface.launch(share=True)