Create app.py

app.py

@@ -0,0 +1,36 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+
+b_tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-560m")#using small parameter version of model for faster inference on hf
+b_model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-560m")
+
+g_tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b")#using small paramerter version of model for faster inference on hf
+g_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b")
+
+def Sentence_Commpletion(model_name, input_text):
+    
+    if model_name == "Bloom":
+        tokenizer, model = b_tokenizer, b_model
+    elif model_name == "Gemma":
+        tokenizer, model = g_tokenizer, g_model
+    
+    
+    
+   inputs = tokenizer(input_text, return_tensors="pt")
+   outputs = model.generate(inputs.input_ids, max_length=50, num_return_sequences=1)
+    
+   return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+
+interface = gr.Interface(
+fn=Sentence_Commpletion,
+inputs=[gr.Radio(["Bloom", "Gemma"], label="Choose model"),
+        
+        gr.Textbox(placeholder="Enter sentece"),],
+    outputs="text",
+    title="Bloom vs Gemma Sentence completion",
+    
+)
+
+
+interface.launch()