added new changes

app.py

@@ -1,29 +1,9 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-3b")
-model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-3b")
-
-def generate_text(prompt):
-    # Tokenize the input prompt
-    inputs = tokenizer.encode(prompt, return_tensors="pt")
-
-    # Generate text based on the prompt
-    output = model.generate(inputs, max_length=100, num_return_sequences=1)
-
-    # Decode the generated output
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-
-    return generated_text
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=generate_text,
-    inputs="text",
-    outputs="text",
-    title="Transformer Text Generation",
-    description="Enter a prompt and the model will generate text based on it.",
-)
-
-# Launch the Gradio interface
-iface.launch()
+import torch
+from transformers import pipeline
+ans = pipeline(model="databricks/dolly-v2-3b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+def answer(query):
+  out=ans(query)
+  return out
+Demo = gr.Interface(fn=answer,inputs='text',outputs='text',examples=[['What is the capital of India ?']])
+Demo.launch()

requirements.txt

@@ -1,4 +1,3 @@
 transformers
 torch 
-torchvision 
-torchaudio
+accelerate