Update README.md
Browse files
README.md
CHANGED
@@ -19,6 +19,9 @@ widget:
|
|
19 |
example_title: "probability distribution"
|
20 |
- text: "question: how does exercise help us lose weight? context: I started working out two weeks ago and already feel a lot better, and started to think about it and became deeply confused."
|
21 |
example_title: "pumpen"
|
|
|
|
|
|
|
22 |
inference:
|
23 |
parameters:
|
24 |
max_length: 64
|
@@ -41,4 +44,4 @@ inference:
|
|
41 |
|
42 |
- for inputs, the model was presented with the post title and the post selftext encoded as: `question: <post title> context: <post selftext>`. You may see better results if queries are posed in this fashion.
|
43 |
- The top two replies were aggregated and presented to the model as the output text.
|
44 |
-
- Training for longer will be explored, but given that the dataset has 127k examples and the loss flatlines at 0.5 epochs this should be fairly viable.
|
|
|
19 |
example_title: "probability distribution"
|
20 |
- text: "question: how does exercise help us lose weight? context: I started working out two weeks ago and already feel a lot better, and started to think about it and became deeply confused."
|
21 |
example_title: "pumpen"
|
22 |
+
- text: "what is a neural network?"
|
23 |
+
example_title: "deep learning"
|
24 |
+
|
25 |
inference:
|
26 |
parameters:
|
27 |
max_length: 64
|
|
|
44 |
|
45 |
- for inputs, the model was presented with the post title and the post selftext encoded as: `question: <post title> context: <post selftext>`. You may see better results if queries are posed in this fashion.
|
46 |
- The top two replies were aggregated and presented to the model as the output text.
|
47 |
+
- Training for longer will be explored, but given that the dataset has 127k examples and the loss flatlines at 0.5 epochs so this model should be fairly viable.
|