adjust model

app.py

@@ -30,8 +30,8 @@ from threading import Thread
 #gr.ChatInterface(predict).launch()
 
 
-tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
-model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf")
+model = AutoModelForCausalLM.from_pretrained("mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf", torch_dtype=torch.float16)
 model = model.to('cuda:0')
 
 class StopOnTokens(StoppingCriteria):