Update README.md

README.md

@@ -64,10 +64,22 @@ language:
 widget:
 - text: "Translate to German:  My name is Arthur"
   example_title: "Translation"
-- text: "Please answer to the following question. Who is going to be the next   ‘Ballon d'or’?"
+- text: "Please answer to the following question. Who is going to be the next Ballon d'or?"
   example_title: "Question Answering"
-- text: "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 apples do they have?"
-  example_title: "Logic puzzles"
+- text: "Q: Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering."
+  example_title: "Logical reasoning"
+- text: "Please answer the following question. What is the boiling point of Nitrogen?"
+  example_title: "Scientific knowledge"
+- text: "Answer the following yes/no question. Can you write a whole Haiku in a single tweet?"
+  example_title: "Yes/no question"
+- text: "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?"
+  example_title: "Reasoning task"
+- text: "Q: ( False or not False or False ) is? A: Let's think step by step"
+  example_title: "Boolean Expressions"
+- text: "The square root of x is the cube root of y. What is y to the power of 2, if x = 4?"
+  example_title: "Math reasoning"
+- text: "Premise:  At my age you will probably have learnt one lesson. Hypothesis:  It's not certain how many lessons you'll learn by your thirties. Does the premise entail the hypothesis?"
+  example_title: "Premise and hypothesis"
 
 tags:
 - text2text-generation
@@ -142,8 +154,8 @@ Find below some example scripts on how to use the model in `transformers`:
 
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
+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
@@ -163,8 +175,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto")
+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")
@@ -187,8 +199,8 @@ print(tokenizer.decode(outputs[0]))
 import torch
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", torch_dtype=torch.float16)
+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")
@@ -208,8 +220,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install bitsandbytes accelerate
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", load_in_8bit=True)
+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")
@@ -280,7 +292,7 @@ For full details, please check the [research paper](https://arxiv.org/pdf/2210.1
 
 ## Results 
 
-For full results for FLAN-T5-Large, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3.
+For full results for FLAN-T5-XXL, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3.
 
 # Environmental Impact