Update app.py

app.py

@@ -1,7 +1,26 @@
 import gradio
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-small", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-small")
 
 def my_inference_function(name):
-  return "Hello " + name + "!"
+    mail="お世話になっております。商品開発部の森本です。先日は貴重な"
+    inputs = tokenizer(f"(上司へのメール敬語で){mail}", return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        tokens = model.generate(
+            **inputs,
+            max_new_tokens=4,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.05,
+            pad_token_id=tokenizer.pad_token_id,
+        )
+    output = tokenizer.decode(tokens[0], skip_special_tokens=True)
+    output=output.replace(f"(上司へのメール敬語で){mail}","")
+  return output.replace("\n", "")
 
 gradio_interface = gradio.Interface(
   fn = my_inference_function,