Add Gradio app for PEFT model

app.py

@@ -1,63 +1,33 @@
 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})
-
-    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)",
-        ),
-    ],
-)
+from transformers import AutoTokenizer
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
+
+# Load the PEFT model configuration and model
+config = PeftConfig.from_pretrained("isashap/contexttrained-validationloss-gpt2FINAL")
+base_model = AutoModelForCausalLM.from_pretrained("gpt2")
+model = PeftModel.from_pretrained(base_model, "isashap/contexttrained-validationloss-gpt2FINAL")
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("gpt2")
+
+# Define the prediction function
+def predict_stock(input_text):
+    # Tokenize the input
+    inputs = tokenizer(input_text, return_tensors="pt")
+    # Generate output using the model
+    outputs = model.generate(**inputs, max_length=50, num_return_sequences=1)
+    # Decode the output
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+demo = gr.Interface(
+    fn=predict_stock,
+    inputs=gr.Textbox(lines=2, label="Input Text (e.g., stock-related news)"),
+    outputs=gr.Textbox(label="Prediction"),
+    title="Stock Prediction with PEFT Model",
+    description="A demo that uses a fine-tuned GPT-2 model with PEFT to predict stock outcomes based on input text."
+    )    
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+transformers
+peft