Update app.py

app.py

@@ -1,7 +1,27 @@
 import gradio as gr
 
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-7b", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-7b")
+
+def proc( inputs ):
+    with torch.no_grad():
+        tokens = model.generate(
+            **inputs,
+            max_new_tokens=64,  # 生成する長さ. 128 とかでも良い.
+            do_sample=True,
+            temperature=0.7,  # 生成のランダム性. 高いほど様々な単語が出てくるが関連性は下がる.
+            pad_token_id=tokenizer.pad_token_id,
+        )
+    
+    return = tokenizer.decode(tokens[0], skip_special_tokens=True)
+
 def greet(name):
-    return "Hello " + name + "!!"
+    inputs = tokenizer(name, return_tensors="pt").to(model.device)
+    outputs = proc( inputs )
+    return( outputs )
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")
 iface.launch()