Create app.py

app.py

@@ -0,0 +1,50 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
+import gradio as gr
+
+# Replace this with your Hugging Face model repo ID
+model_repo = "nambn0321/LLM_model"
+
+# Load LoRA adapter config from the Hub
+peft_config = PeftConfig.from_pretrained(model_repo)
+
+# Load base model (will automatically download from Hub)
+base_model = AutoModelForCausalLM.from_pretrained(
+    peft_config.base_model_name_or_path,
+    return_dict=True,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# Load adapter weights from your fine-tuned repo
+model = PeftModel.from_pretrained(base_model, model_repo)
+
+# Load tokenizer from the Hub repo
+tokenizer = AutoTokenizer.from_pretrained(model_repo, use_fast=False)
+
+def generate_response(prompt, max_tokens=128, temperature=0.7, top_p=0.9):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        do_sample=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(lines=4, label="Prompt"),
+        gr.Slider(16, 512, value=128, step=16, label="Max Tokens"),
+        gr.Slider(0.1, 1.5, value=0.7, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.9, label="Top-p")
+    ],
+    outputs="text",
+    title="Fine-Tuned LLM",
+    description="Interact with your fine-tuned model hosted on Hugging Face Hub."
+)
+
+iface.launch()