Update app.py

app.py

@@ -1,64 +1,59 @@
 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)",
-        ),
-    ],
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load your hosted model and tokenizer from Hugging Face.
+model_name = "Samurai719214/gptneo-mythology-storyteller"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Use GPU if available.
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def generate_full_story(excerpt: str) -> str:
+    """
+    Given an incomplete story excerpt (without header details), this function calls the model 
+    to generate the complete story that includes Parv, Key Event, Section and the story continuation.
+    """
+    # Tokenize the user-provided excerpt.
+    encoded_input = tokenizer(excerpt, return_tensors="pt")
+    # Move tensors to the appropriate device.
+    encoded_input = {k: v.to(device) for k, v in encoded_input.items()}
+    
+    # Generate tokens. Here, we set parameters to control length and creativity.
+    output = model.generate(
+        encoded_input["input_ids"],
+        attention_mask=encoded_input["attention_mask"],
+        max_new_tokens=200,         # Generate 200 new tokens on top of the input.
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.95,
+        no_repeat_ngram_size=2,
+        return_dict_in_generate=True
+    )
+    
+    # Decode the generated sequence.
+    generated_text = tokenizer.decode(output.sequences[0], skip_special_tokens=True)
+    
+    return generated_text
+
+# Build the Gradio interface.
+interface = gr.Interface(
+    fn=generate_full_story,
+    inputs=gr.Textbox(
+        lines=5,
+        label="Incomplete Story Excerpt",
+        placeholder="Enter your incomplete story excerpt here..."
+    ),
+    outputs=gr.Textbox(label="Complete Story with Details"),
+    title="Mythology Storyteller",
+    description=(
+        "Enter an incomplete story excerpt. "
+        "The model will generate a complete output that includes the chapter (Parv), key event, section, "
+        "and the full story continuation."
+    )
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app.
+interface.launch(share=True)