Add application file

app.py

@@ -5,7 +5,6 @@ from threading import Thread
 
 tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
 model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
-model = model.to('cuda:0')
 
 class StopOnTokens(StoppingCriteria):
     def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
@@ -22,7 +21,7 @@ def predict(message, history):
     messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
                 for item in history_transformer_format])
 
-    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    model_inputs = tokenizer([messages], return_tensors="pt")
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,