Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    trust_remote_code=True,
+    device_map="auto",
+    low_cpu_mem_usage=True,
+
+)
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
+
+
+def generate_text(input_text):
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+    attention_mask = torch.ones(input_ids.shape)
+
+
+    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(output_text)
+
+
+    # Remove Prompt Echo from Generated Text
+    cleaned_output_text = output_text.replace(input_text, "")
+    return cleaned_output_text
+
+
+text_generation_interface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.inputs.Textbox(label="Input Text"),
+    ],