mohamedemam
commited on
Commit
•
6be6652
1
Parent(s):
037b31d
Update README.md
Browse files
README.md
CHANGED
@@ -27,6 +27,18 @@ tags:
|
|
27 |
|
28 |
# Model Card for QA_GeneraToR
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/flan2_architecture.jpg"
|
31 |
alt="drawing" width="600"/>
|
32 |
|
@@ -42,16 +54,7 @@ alt="drawing" width="600"/>
|
|
42 |
7. [Environmental Impact](#environmental-impact)
|
43 |
8. [Citation](#citation)
|
44 |
9. [Model Card Authors](#model-card-authors)
|
45 |
-
|
46 |
-
>This model is fine tuned to generate a question with answers from a context , why that can be very usful this can help you to generate a dataset from a book article any thing you would to make from it dataset and train another model on this dataset , give the model any context with pre prometed of quation you want + context and it will extarct question + answer for you
|
47 |
-
this are promted i use
|
48 |
-
>[ "which", "how", "when", "where", "who", "whom", "whose", "why",
|
49 |
-
"which", "who", "whom", "whose", "whereas",
|
50 |
-
"can", "could", "may", "might", "will", "would", "shall", "should",
|
51 |
-
"do", "does", "did", "is", "are", "am", "was", "were", "be", "being", "been",
|
52 |
-
"have", "has", "had", "if", "is", "are", "am", "was", "were", "do", "does", "did", "can", "could",
|
53 |
-
"will", "would", "shall", "should", "might", "may", "must",
|
54 |
-
"may", "might", "must"]
|
55 |
# TL;DR
|
56 |
|
57 |
If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
|
|
|
27 |
|
28 |
# Model Card for QA_GeneraToR
|
29 |
|
30 |
+
# my fine tuned model
|
31 |
+
>This model is fine tuned to generate a question with answers from a context , why that can be very usful this can help you to generate a dataset from a book article any thing you would to make from it dataset and train another model on this dataset , give the model any context with pre prometed of quation you want + context and it will extarct question + answer for you
|
32 |
+
this are promted i use
|
33 |
+
>[ "which", "how", "when", "where", "who", "whom", "whose", "why",
|
34 |
+
"which", "who", "whom", "whose", "whereas",
|
35 |
+
"can", "could", "may", "might", "will", "would", "shall", "should",
|
36 |
+
"do", "does", "did", "is", "are", "am", "was", "were", "be", "being", "been",
|
37 |
+
"have", "has", "had", "if", "is", "are", "am", "was", "were", "do", "does", "did", "can", "could",
|
38 |
+
"will", "would", "shall", "should", "might", "may", "must",
|
39 |
+
"may", "might", "must"]
|
40 |
+
>
|
41 |
+
# orignal model info
|
42 |
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/flan2_architecture.jpg"
|
43 |
alt="drawing" width="600"/>
|
44 |
|
|
|
54 |
7. [Environmental Impact](#environmental-impact)
|
55 |
8. [Citation](#citation)
|
56 |
9. [Model Card Authors](#model-card-authors)
|
57 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
# TL;DR
|
59 |
|
60 |
If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
|