Update README.md
Browse files
README.md
CHANGED
|
@@ -1,26 +1,31 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
inference:
|
| 4 |
parameters:
|
| 5 |
num_beams: 3
|
| 6 |
num_beam_groups: 3
|
| 7 |
num_return_sequences: 1
|
| 8 |
-
repetition_penalty: 3
|
| 9 |
diversity_penalty: 3.01
|
| 10 |
no_repeat_ngram_size: 2
|
| 11 |
temperature: 0.8
|
| 12 |
max_length: 64
|
| 13 |
widget:
|
| 14 |
- text: >-
|
| 15 |
-
paraphraser: Learn to build generative AI applications with an expert AWS
|
|
|
|
|
|
|
| 16 |
example_title: AWS course
|
| 17 |
- text: >-
|
| 18 |
-
paraphraser: In healthcare, Generative AI can help generate synthetic
|
|
|
|
|
|
|
| 19 |
example_title: Generative AI
|
| 20 |
- text: >-
|
| 21 |
-
paraphraser: By leveraging prior model training through transfer learning,
|
| 22 |
-
can reduce the amount of expensive computing power and labeled
|
| 23 |
-
to obtain large models tailored to niche use cases and business
|
|
|
|
| 24 |
example_title: Fine Tuning
|
| 25 |
extra_gated_fields:
|
| 26 |
geo: ip_location
|
|
|
|
| 1 |
---
|
| 2 |
+
license: openrail
|
| 3 |
inference:
|
| 4 |
parameters:
|
| 5 |
num_beams: 3
|
| 6 |
num_beam_groups: 3
|
| 7 |
num_return_sequences: 1
|
| 8 |
+
repetition_penalty: 3
|
| 9 |
diversity_penalty: 3.01
|
| 10 |
no_repeat_ngram_size: 2
|
| 11 |
temperature: 0.8
|
| 12 |
max_length: 64
|
| 13 |
widget:
|
| 14 |
- text: >-
|
| 15 |
+
paraphraser: Learn to build generative AI applications with an expert AWS
|
| 16 |
+
instructor with the 2-day Developing Generative AI Applications on AWS
|
| 17 |
+
course.
|
| 18 |
example_title: AWS course
|
| 19 |
- text: >-
|
| 20 |
+
paraphraser: In healthcare, Generative AI can help generate synthetic
|
| 21 |
+
medical data to train machine learning models, develop new drug candidates,
|
| 22 |
+
and design clinical trials.
|
| 23 |
example_title: Generative AI
|
| 24 |
- text: >-
|
| 25 |
+
paraphraser: By leveraging prior model training through transfer learning,
|
| 26 |
+
fine-tuning can reduce the amount of expensive computing power and labeled
|
| 27 |
+
data needed to obtain large models tailored to niche use cases and business
|
| 28 |
+
needs.
|
| 29 |
example_title: Fine Tuning
|
| 30 |
extra_gated_fields:
|
| 31 |
geo: ip_location
|