Update README.md

Update usage sample code

README.md

@@ -36,18 +36,17 @@ This model can be used for text-to-text generation tasks like question answering
 
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+import torch
 
-tokenizer = AutoTokenizer.from_pretrained("iarroyof/t5-11b-ssm-nq-sharded")
+tokenizer = AutoTokenizer.from_pretrained('iarroyof/t5-11b-ssm-nq-sharded')
 model = AutoModelForSeq2SeqLM.from_pretrained(
-    "iarroyof/t5-11b-ssm-nq-sharded",
-    device_map="auto",
-    max_memory={0: "40GB", 1: "40GB", "cpu": "30GB"},
+    'iarroyof/t5-11b-ssm-nq-sharded',
+    device_map='auto',
     low_cpu_mem_usage=True,
     torch_dtype=torch.float16,
-    trust_remote_code=True
 )
 
-inputs = tokenizer("Translate English to French: How are you?", return_tensors="pt").input_ids
+inputs = tokenizer('What is and how to deal with insomnia?', return_tensors='pt').input_ids.to('cuda')
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ---