Upload model.py

model.py

@@ -6,18 +6,16 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 model_id = 'elyza/ELYZA-japanese-Llama-2-7b-instruct'
-if torch.cuda.is_available():
-    model = AutoModelForCausalLM.from_pretrained(
-        model_id,
-        torch_dtype=torch.bfloat16,
-        device_map='auto',
-        use_auth_token=True,
-        use_cache=True,
-    ).float()
-else:
-    model = None
-tokenizer = AutoTokenizer.from_pretrained(model_id)
 
+# トークナイザーとモデルの準備
+tokenizer = AutoTokenizer.from_pretrained(
+    "elyza/ELYZA-japanese-Llama-2-7b-instruct"
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "elyza/ELYZA-japanese-Llama-2-7b-instruct", 
+    torch_dtype=torch.float16,
+    device_map="auto"
+).float()
 
 def get_prompt(message: str, chat_history: list[tuple[str, str]],
                system_prompt: str) -> str: