Changed app.py

app.py

@@ -1,23 +1,35 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import transformers
+from transformers import AutoTokenizer
+model = "anirudh-sub/debate_model_v2.1"
+tokenizer = AutoTokenizer.from_pretrained(model)
 
-model_name = "anirudh-sub/debate_model_v2"
-model = AutoModelForCausalLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    device_map="auto",
+)
 
-def generate_text(prompt):
-    input_ids = tokenizer.encode(prompt, return_tensors="pt")
-    output = model.generate(input_ids, max_length=100, num_return_sequences=1)
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-    return generated_text
+def generate_text(text):
+    return "hello" + text
+    sequences = pipeline(
+        text,
+        do_sample=True,
+        top_k=10,
+        num_return_sequences=1,
+        eos_token_id=tokenizer.eos_token_id,
+        max_length=500,
+    )
+    response = ""
+    for seq in sequences:
+        print(f"Result: {seq['generated_text']}")
+        response += {seq['generated_text']}
+    return response
 
 iface = gr.Interface(
     fn=generate_text,
-    inputs="text",
+    inputs=gr.Textbox(),
     outputs="text",
-    live=True,
-    title="Debate Model",
-    description="This model generates text based on the input prompt using Llama.",
 )
 
 iface.launch()