Update app.py

app.py

@@ -1,64 +1,75 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-"""
-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")
+class TextGenerator:
+    def __init__(self, model_name, device='cpu'):
+        self.device = device
+        self.load_model(model_name)
 
+    def load_model(self, model_name):
+        # Load model and tokenizer from Hugging Face
+        print("Loading model and tokenizer...")
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name)
+        self.model.to(self.device)
+        print("Model loaded successfully!")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    def generate_text(self, prompt, max_length=100, temperature=0.7, top_k=50, top_p=0.9):
+        # Tokenize input
+        input_ids = self.tokenizer.encode(prompt, return_tensors="pt").to(self.device)
+        
+        # Generate text
+        with torch.no_grad():
+            output_ids = self.model.generate(
+                input_ids,
+                max_length=max_length,
+                temperature=temperature,
+                top_k=top_k,
+                top_p=top_p,
+                do_sample=True,
+                pad_token_id=self.tokenizer.eos_token_id
+            )
+        
+        # Decode output tokens
+        generated_text = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
+        return generated_text
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def create_gradio_interface(model_name):
+    generator = TextGenerator(model_name)
 
-    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)",
-        ),
-    ],
-)
+    def generate(prompt, max_length, temperature, top_k, top_p):
+        try:
+            return generator.generate_text(
+                prompt=prompt,
+                max_length=max_length,
+                temperature=temperature,
+                top_k=top_k,
+                top_p=top_p
+            )
+        except Exception as e:
+            return f"Error: {str(e)}"
 
+    # Define Gradio interface
+    interface = gr.Interface(
+        fn=generate,
+        inputs=[
+            gr.Textbox(label="Prompt", placeholder="Enter your prompt here..."),
+            gr.Slider(minimum=10, maximum=500, value=100, step=10, label="Maximum Length"),
+            gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
+            gr.Slider(minimum=0, maximum=100, value=50, step=5, label="Top-k"),
+            gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.1, label="Top-p"),
+        ],
+        outputs=gr.Textbox(label="Generated Text"),
+        title="Reality123b/Xylaria-1.4-Senoa-Test",
+        description="Generate text using the Reality123b/Xylaria-1.4-Senoa-Test model optimized for CPU usage.",
+    )
+    return interface
 
 if __name__ == "__main__":
-    demo.launch()
+    # Use the model from Hugging Face
+    model_name = "Reality123b/Xylaria-1.4-Senoa-Test"
+    
+    # Create and launch Gradio interface
+    interface = create_gradio_interface(model_name)
+    interface.launch(share=True)