Update app.py

app.py

@@ -1,64 +1,38 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 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)",
-        ),
+# Load model and tokenizer
+model_name = "tomg-group-umd/huginn-0125"
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Function to generate text
+def generate_response(prompt, num_steps):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    
+    input_ids = tokenizer.encode(prompt, return_tensors="pt").to(device)
+    model.eval()
+    
+    with torch.no_grad():
+        output = model.generate(input_ids, num_steps=num_steps, max_length=256)
+    
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(lines=5, label="Input Prompt"),
+        gr.Slider(minimum=4, maximum=64, step=1, value=16, label="Computation Scale (num_steps)")
     ],
+    outputs="text",
+    title="Huginn-0125 Text Generation",
+    description="Generate text using the Huginn-0125 model with adjustable computation scale."
 )
 
-
+# Run app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()