Create app.py

app.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+gr.load("models/bigcode/starcoder2-7b").launch()
+
+checkpoint = "bigcode/starcoder2-7b"
+device = "cuda" # for GPU usage or "cpu" for CPU usage
+
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+
+inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))