AutoModelForConditionalGeneration -> T5ForConditionalGeneration

README.md

@@ -100,9 +100,9 @@ For more efficient memory usage, we advise you to load the model in `8bit` using
 
 ```python
 # pip install accelerate transformers bitsandbytes
-from transformers import AutoModelForConditionalGeneration, AutoTokenizer
+from transformers import T5ForConditionalGeneration, AutoTokenizer
 import torch
-model = AutoModelForConditionalGeneration.from_pretrained("google/flan-ul2", device_map="auto", load_in_8bit=True)                                                                 
+model = T5ForConditionalGeneration.from_pretrained("google/flan-ul2", device_map="auto", load_in_8bit=True)                                                                 
 tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2")
 
 input_string = "Answer the following question by reasoning step by step. The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?"                                               
@@ -118,9 +118,9 @@ Otherwise, you can load and run the model in `bfloat16` as follows:
 
 ```python
 # pip install accelerate transformers
-from transformers import AutoModelForConditionalGeneration, AutoTokenizer
+from transformers import T5ForConditionalGeneration, AutoTokenizer
 import torch
-model = AutoModelForConditionalGeneration.from_pretrained("google/flan-ul2", torch_dtype=torch.bfloat16, device_map="auto")                                                                 
+model = T5ForConditionalGeneration.from_pretrained("google/flan-ul2", torch_dtype=torch.bfloat16, device_map="auto")                                                                 
 tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2")
 
 input_string = "Answer the following question by reasoning step by step. The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?"