google
/

flan-t5-xxl

Text2Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ybelkada commited on Oct 22, 2022

Commit

2d8b933

•

1 Parent(s): 0657afd

Update README.md

Correct inference script

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -158,7 +158,7 @@ tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl")
 input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
@@ -179,7 +179,7 @@ tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto")
 input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
@@ -203,7 +203,7 @@ tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", torch_dtype=torch.float16)
 input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
@@ -224,7 +224,7 @@ tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", load_in_8bit=True)
 input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))

 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl")
 input_text = "translate English to German: How old are you?"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto")
 input_text = "translate English to German: How old are you?"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", torch_dtype=torch.float16)
 input_text = "translate English to German: How old are you?"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", load_in_8bit=True)
 input_text = "translate English to German: How old are you?"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
 outputs = model.generate(input_ids)
 print(tokenizer.decode(outputs[0]))