|
--- |
|
|
|
language: |
|
- en |
|
tags: |
|
- t5 |
|
datasets: |
|
- eli5 |
|
metrics: |
|
- rouge |
|
widget: |
|
- text: "why aren't there more planets in our solar system?" |
|
example_title: "solar system" |
|
- text: "question: what is a probability distribution? context: I am just learning about statistics." |
|
example_title: "probability distribution" |
|
- 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." |
|
example_title: "pumpen" |
|
inference: |
|
parameters: |
|
max_length: 128 |
|
no_repeat_ngram_size: 2 |
|
encoder_no_repeat_ngram_size: 3 |
|
repetition_penalty: 2.4 |
|
length_penalty: 0.5 |
|
num_beams: 2 |
|
early_stopping: True |
|
|
|
--- |
|
|
|
# t5 - base- askscience |
|
|
|
- the entirety of askscience sub-section of eli5 dataset for one epoch. |
|
- compare to bart on eli5 [here](https://huggingface.co/yjernite/bart_eli5) |
|
- note that for the inference API here, the model is restricted to outputting 128 tokens - using the model in python with the transformers library, you can get longer outputs. |
|
|
|
## training |
|
|
|
- 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. |
|
- The top two replies were aggregated and presented to the model as the output text. |
