Update app.py

app.py

@@ -1,64 +1,34 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+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")
+BASE_MODEL = "meta-llama/Llama-2-7b-hf"
+ADAPTER = "thangduong0509/vinallama-peft-7b-math-solver"
 
-
-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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        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)",
-        ),
-    ],
+# Load base model
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
+base_model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    device_map="auto",
+    torch_dtype=torch.float16,
+    trust_remote_code=True
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Load PEFT adapter
+model = PeftModel.from_pretrained(base_model, ADAPTER)
+model.eval()
+
+def solve_math(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+gr.Interface(
+    fn=solve_math,
+    inputs=gr.Textbox(lines=3, placeholder="Nhập đề Toán tiểu học..."),
+    outputs="text",
+    title="🧮 ViLLama Math Solver",
+    description="Giải toán tiểu học bằng mô hình LLaMA-2 7B fine-tune với PEFT"
+).launch()