Translation
Transformers
PyTorch
Safetensors
English
t5
text2text-generation
united states air force
united states space force
department of defense
dod
usaf
ussf
afi
air force
space force
bullets
performance reports
evaluations
awards
opr
epr
narratives
interpreter
mbzuai
lamini-flan-t5-783m
flan-t5
google
opera
justinthelaw
text-generation-inference
Inference Endpoints
Justin Law
commited on
Commit
•
7749ef1
1
Parent(s):
2e28dda
Docs(README): Example cleaning for inference
Browse files
README.md
CHANGED
@@ -29,12 +29,8 @@ tags:
|
|
29 |
- opera
|
30 |
- justinthelaw
|
31 |
widget:
|
32 |
-
- text: "Using
|
33 |
-
example_title: "
|
34 |
-
- text: "Using upwards of 3 sentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context that is not already included in the Air and Space Force bullet statement: - Steered F22 DMS ops; led 9 mbrs/provided 24 hr MXS spt/returned 54 AFREP items--saved $258K/nailed 2K sorties"
|
35 |
-
example_title: "Bullet Interpretation 2"
|
36 |
-
- text: "Using upwards of 3 sentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context that is not already included in the Air and Space Force bullet statement: - Setup Ex KEY RESOLVE '10 comms; installed 35 linesran 500ft cabling--supported multi-national operations"
|
37 |
-
example_title: "Bullet Interpretation 3"
|
38 |
---
|
39 |
|
40 |
# Opera Bullet Interpreter
|
@@ -88,7 +84,7 @@ Used to programmatically produce training data for Opera's Bullet Forge (see
|
|
88 |
The exact prompt to achieve the desired result is:
|
89 |
|
90 |
```
|
91 |
-
Using
|
92 |
```
|
93 |
|
94 |
## Downstream Use
|
@@ -205,7 +201,7 @@ import torch
|
|
205 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
206 |
|
207 |
bullet_data_creation_prefix = (
|
208 |
-
"Using
|
209 |
+ "spelling-out acronyms and adding additional context that is not already included in the " +
|
210 |
"Air and Space Force bullet statement: "
|
211 |
)
|
|
|
29 |
- opera
|
30 |
- justinthelaw
|
31 |
widget:
|
32 |
+
- text: "Using full sentencessentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context that is not already included in the Air and Space Force bullet statement: - Attended 4-hour EPD Instructor training; taught 3 2-hour Wing EPD & 4 1-hour bullet writing courses--prepared 164 for leadership"
|
33 |
+
example_title: "Example Usage"
|
|
|
|
|
|
|
|
|
34 |
---
|
35 |
|
36 |
# Opera Bullet Interpreter
|
|
|
84 |
The exact prompt to achieve the desired result is:
|
85 |
|
86 |
```
|
87 |
+
Using full sentencessentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context that is not already included in the Air and Space Force bullet statement: <INSERT BULLET HERE>"
|
88 |
```
|
89 |
|
90 |
## Downstream Use
|
|
|
201 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
202 |
|
203 |
bullet_data_creation_prefix = (
|
204 |
+
"Using full sentencessentences, expand upon the following Air and Space Force bullet statement by "
|
205 |
+ "spelling-out acronyms and adding additional context that is not already included in the " +
|
206 |
"Air and Space Force bullet statement: "
|
207 |
)
|