fixed examples
Browse files
app.py
CHANGED
@@ -75,8 +75,7 @@ Question: What is the currency of Switzerland?
|
|
75 |
Answer: Swiss franc
|
76 |
|
77 |
Question: In which country is Wisconsin located?
|
78 |
-
Answer:
|
79 |
-
''', "GPT-JT-6B-v1", 5, 0.0, 1.0, 40],
|
80 |
[
|
81 |
# Sentiment Analysis
|
82 |
'''Label the tweets as either "positive", "negative", "mixed", or "neutral":
|
@@ -94,7 +93,7 @@ Tweet: I think the background image could have been better.
|
|
94 |
Label: negative
|
95 |
|
96 |
Tweet: I really like it.
|
97 |
-
Label:
|
98 |
[
|
99 |
# Topic Classification
|
100 |
'''Given a news article, classify its topic.
|
@@ -107,8 +106,7 @@ Article: Soaring crude prices plus worries about the economy and the outlook for
|
|
107 |
Label: Business
|
108 |
|
109 |
Article: Murtagh a stickler for success Northeastern field hockey coach Cheryl Murtagh doesn't want the glare of the spotlight that shines on her to detract from a team that has been the America East champion for the past three years and has been to the NCAA tournament 13 times.
|
110 |
-
Label:
|
111 |
-
''', "GPT-JT-6B-v1", 5, 0.0, 1.0, 40],
|
112 |
[
|
113 |
# Paraphrasing
|
114 |
'''Paraphrase the given sentence into a different sentence.
|
@@ -120,8 +118,7 @@ Input: What are the famous places we should not miss in Paris?
|
|
120 |
Output: Recommend some of the best places to visit in Paris?
|
121 |
|
122 |
Input: Could you recommend some hotels that have cheap price in Zurich?
|
123 |
-
Output:
|
124 |
-
''', "GPT-JT-6B-v1", 20, 0.8, 1.0, 40],
|
125 |
[
|
126 |
# Text Summarization
|
127 |
'''Given a review from Amazon's food products, the task is to generate a short summary of the given review in the input.
|
@@ -133,8 +130,7 @@ Input: Product arrived labeled as Jumbo Salted Peanuts...the peanuts were actual
|
|
133 |
Output: Not as Advertised
|
134 |
|
135 |
Input: My toddler loves this game to a point where he asks for it. That's a big thing for me. Secondly, no glitching unlike one of their competitors (PlayShifu). Any tech I don’t have to reach out to support for help is a good tech for me. I even enjoy some of the games and activities in this. Overall, this is a product that shows that the developers took their time and made sure people would not be asking for refund. I’ve become bias regarding this product and honestly I look forward to buying more of this company’s stuff. Please keep up the great work.
|
136 |
-
Output:
|
137 |
-
''', "GPT-JT-6B-v1", 10, 0.0, 1.0, 40],
|
138 |
[
|
139 |
# Word Sense Disambiguation
|
140 |
'''Identify which sense of a word is meant in a given context.
|
@@ -153,8 +149,7 @@ Sense: commercial (finance) banks
|
|
153 |
|
154 |
Context: Bill killed the project
|
155 |
Word: kill
|
156 |
-
Sense:
|
157 |
-
''', "GPT-JT-6B-v1", 10, 0.0, 1.0, 40],
|
158 |
[
|
159 |
# Natural Language Interface
|
160 |
'''Given a pair of sentences, choose whether the two sentences agree (entailment)/disagree (contradiction) with each other.
|
@@ -167,8 +162,7 @@ Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a
|
|
167 |
Label: contradiction
|
168 |
|
169 |
Sentence 1: Two middle-aged people stand by a golf hole. Sentence 2: A couple riding in a golf cart.
|
170 |
-
Label:
|
171 |
-
''', "GPT-JT-6B-v1", 2, 0.0, 1.0, 40]
|
172 |
]
|
173 |
|
174 |
|
|
|
75 |
Answer: Swiss franc
|
76 |
|
77 |
Question: In which country is Wisconsin located?
|
78 |
+
Answer:''', "GPT-JT-6B-v1", 5, 0.0, 1.0, 40],
|
|
|
79 |
[
|
80 |
# Sentiment Analysis
|
81 |
'''Label the tweets as either "positive", "negative", "mixed", or "neutral":
|
|
|
93 |
Label: negative
|
94 |
|
95 |
Tweet: I really like it.
|
96 |
+
Label:''', "GPT-JT-6B-v1", 2, 0.0, 1.0, 40],
|
97 |
[
|
98 |
# Topic Classification
|
99 |
'''Given a news article, classify its topic.
|
|
|
106 |
Label: Business
|
107 |
|
108 |
Article: Murtagh a stickler for success Northeastern field hockey coach Cheryl Murtagh doesn't want the glare of the spotlight that shines on her to detract from a team that has been the America East champion for the past three years and has been to the NCAA tournament 13 times.
|
109 |
+
Label:''', "GPT-JT-6B-v1", 5, 0.0, 1.0, 40],
|
|
|
110 |
[
|
111 |
# Paraphrasing
|
112 |
'''Paraphrase the given sentence into a different sentence.
|
|
|
118 |
Output: Recommend some of the best places to visit in Paris?
|
119 |
|
120 |
Input: Could you recommend some hotels that have cheap price in Zurich?
|
121 |
+
Output:''', "GPT-JT-6B-v1", 20, 0.8, 1.0, 40],
|
|
|
122 |
[
|
123 |
# Text Summarization
|
124 |
'''Given a review from Amazon's food products, the task is to generate a short summary of the given review in the input.
|
|
|
130 |
Output: Not as Advertised
|
131 |
|
132 |
Input: My toddler loves this game to a point where he asks for it. That's a big thing for me. Secondly, no glitching unlike one of their competitors (PlayShifu). Any tech I don’t have to reach out to support for help is a good tech for me. I even enjoy some of the games and activities in this. Overall, this is a product that shows that the developers took their time and made sure people would not be asking for refund. I’ve become bias regarding this product and honestly I look forward to buying more of this company’s stuff. Please keep up the great work.
|
133 |
+
Output:''', "GPT-JT-6B-v1", 10, 0.0, 1.0, 40],
|
|
|
134 |
[
|
135 |
# Word Sense Disambiguation
|
136 |
'''Identify which sense of a word is meant in a given context.
|
|
|
149 |
|
150 |
Context: Bill killed the project
|
151 |
Word: kill
|
152 |
+
Sense:''', "GPT-JT-6B-v1", 10, 0.0, 1.0, 40],
|
|
|
153 |
[
|
154 |
# Natural Language Interface
|
155 |
'''Given a pair of sentences, choose whether the two sentences agree (entailment)/disagree (contradiction) with each other.
|
|
|
162 |
Label: contradiction
|
163 |
|
164 |
Sentence 1: Two middle-aged people stand by a golf hole. Sentence 2: A couple riding in a golf cart.
|
165 |
+
Label:''', "GPT-JT-6B-v1", 2, 0.0, 1.0, 40]
|
|
|
166 |
]
|
167 |
|
168 |
|