bard

app.py

@@ -1,22 +1,25 @@
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
 import gradio as gr
-import subprocess  # Import subprocess module to run shell commands
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-# Install Rust using shell command
-subprocess.run(['curl', '--proto', '=https', '--tlsv1.2', '-sSf', 'https://sh.rustup.rs', '|', 'sh'])
+# Load your pretrained model and tokenizer
+model_name = "your-model-name"  # Replace with your model's name
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 
-# Load pre-trained GPT-2 model and tokenizer
-model_name = "gpt2"  # You can use other models like "gpt2-medium", "gpt2-large", etc.
-model = GPT2LMHeadModel.from_pretrained(model_name)
-tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_answer,
+    inputs=[gr.Textbox(lines=5, placeholder="Ask a question")],
+    outputs="textbox",
+    title="AI Answer Generator",
+)
 
-# Function to generate response
-def generate_response(query):
-    input_ids = tokenizer.encode(query, return_tensors="pt")
-    output = model.generate(input_ids, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2)
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
-    return response
+# Function to generate an answer using your model
+def generate_answer(question):
+    inputs = tokenizer([question], return_tensors="pt")
+    outputs = model.generate(**inputs)
+    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return answer
 
-# Interface setup
-iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Generative AI Query Response")
+# Launch the interface
 iface.launch()