minor

README.md

@@ -110,7 +110,7 @@ assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade tr
 
 # init
 tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-Base-INCITE-2.8B-v1")
-model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-Base-INCITE-2.8B-v1", torch_dtype=torch.float32)
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-Base-INCITE-2.8B-v1", torch_dtype=torch.bfloat16)
 # infer
 prompt = "Alan Turing is"
 inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
@@ -122,11 +122,11 @@ token = outputs.sequences[0, input_length:]
 output_str = tokenizer.decode(token)
 print(output_str)
 """
-one of the most famous people to have come out of Cambridge. He is also one of the most famous people to have been arrested for homosexuality.
+a name that is synonymous with the history of computer science. As the man who invented the Turing machine, the mathematical model that defines the limits of what can be computed, Turing is credited with the invention of the modern computer. Turing was also a mathematician and logician, and his work in these fields led to the development of the field of artificial intelligence...
 """
 ```
 
-Please note that since `LayerNormKernelImpl` is not implemented in fp16 for CPU, we use fp32 for CPU inference.
+Please note that since `LayerNormKernelImpl` is not implemented in fp16 for CPU, we use `bfloat16` for CPU inference.
 
 # Uses