Add PEFT model hosting app

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the PEFT model and tokenizer from Hugging Face Hub
+model_name = "JamieAi33/Phi-2_PEFT"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Define the prediction function
+def generate_text(prompt, max_length=100):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=max_length)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# PEFT LLM Demo")
+    gr.Markdown("Generate text using the Phi-2 PEFT model.")
+    with gr.Row():
+        prompt_input = gr.Textbox(label="Input Prompt", placeholder="Enter a prompt here...")
+        max_tokens_input = gr.Slider(label="Max Tokens", minimum=10, maximum=200, value=

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+transformers