Update app.py

app.py

@@ -1,13 +1,13 @@
 
 hf_token="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"
 
-from transformers import TFAutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 # from transformers.src.transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_id = "meta-llama/Llama-2-13b-chat-hf"
 
 # load the model using 4bit quantization (https://huggingface.co/blog/4bit-transformers-bitsandbytes)
-model = TFAutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, use_auth_token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, use_auth_token=hf_token)
 # disable Tensor Parallelism (https://github.com/huggingface/transformers/pull/24906)
 model.config.pretraining_tp=1