Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,9 @@ language:
|
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
- t5
|
|
|
|
|
|
|
|
|
|
| 7 |
datasets:
|
| 8 |
- eli5
|
| 9 |
metrics:
|
|
@@ -29,9 +32,9 @@ inference:
|
|
| 29 |
|
| 30 |
# t5 - base- askscience
|
| 31 |
|
| 32 |
-
- the entirety of
|
| 33 |
- compare to bart on eli5 [here](https://huggingface.co/yjernite/bart_eli5)
|
| 34 |
-
- note that for the inference API
|
| 35 |
|
| 36 |
## training
|
| 37 |
|
|
|
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
- t5
|
| 7 |
+
- qa
|
| 8 |
+
- askscience
|
| 9 |
+
- lfqa
|
| 10 |
datasets:
|
| 11 |
- eli5
|
| 12 |
metrics:
|
|
|
|
| 32 |
|
| 33 |
# t5 - base- askscience
|
| 34 |
|
| 35 |
+
- [t5-v1_1](google/t5-v1_1-base) trained on the entirety of the _askscience_ sub-section of the eli5 dataset for one epoch.
|
| 36 |
- compare to bart on eli5 [here](https://huggingface.co/yjernite/bart_eli5)
|
| 37 |
+
- note that for the inference API, the model is restricted to outputting 64 tokens - by using the model in python with the transformers library, you can get longer outputs.
|
| 38 |
|
| 39 |
## training
|
| 40 |
|