MImindcrime·Feb 7, 2022Submission
PromptSource: Toolkit for creating, sharing and using natural language prompts
1 points · Open discussionbigscience-workshop
promptsource
Python2021–2022
bigscience-workshop / promptsource
promptsource
Toolkit for creating, sharing and using natural language prompts.
4Distinct people
4Mentions
0Explicit recommenders
3KGitHub stars
What to know before exploring
What it is
Toolkit for creating, sharing and using natural language prompts.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 1:49:46 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week4 dated mentions
Observed mentions: 2021-10-18 14:20:54 UTC to 2022-02-07 18:21:06 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Oct 18 | 2021-10-18 00:00:00 UTC | 2021-10-25 00:00:00 UTC | 3 | 0 | 3 |
| Oct 25 | 2021-10-25 00:00:00 UTC | 2021-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 1 | 2021-11-01 00:00:00 UTC | 2021-11-08 00:00:00 UTC | 0 | 0 | 0 |
| Nov 8 | 2021-11-08 00:00:00 UTC | 2021-11-15 00:00:00 UTC | 0 | 0 | 0 |
| Nov 15 | 2021-11-15 00:00:00 UTC | 2021-11-22 00:00:00 UTC | 0 | 0 | 0 |
| Nov 22 | 2021-11-22 00:00:00 UTC | 2021-11-29 00:00:00 UTC | 0 | 0 | 0 |
| Nov 29 | 2021-11-29 00:00:00 UTC | 2021-12-06 00:00:00 UTC | 0 | 0 | 0 |
| Dec 6 | 2021-12-06 00:00:00 UTC | 2021-12-13 00:00:00 UTC | 0 | 0 | 0 |
| Dec 13 | 2021-12-13 00:00:00 UTC | 2021-12-20 00:00:00 UTC | 0 | 0 | 0 |
| Dec 20 | 2021-12-20 00:00:00 UTC | 2021-12-27 00:00:00 UTC | 0 | 0 | 0 |
| Dec 27 | 2021-12-27 00:00:00 UTC | 2022-01-03 00:00:00 UTC | 0 | 0 | 0 |
| Jan 3 | 2022-01-03 00:00:00 UTC | 2022-01-10 00:00:00 UTC | 0 | 0 | 0 |
| Jan 10 | 2022-01-10 00:00:00 UTC | 2022-01-17 00:00:00 UTC | 0 | 0 | 0 |
| Jan 17 | 2022-01-17 00:00:00 UTC | 2022-01-24 00:00:00 UTC | 0 | 0 | 0 |
| Jan 24 | 2022-01-24 00:00:00 UTC | 2022-01-31 00:00:00 UTC | 0 | 0 | 0 |
| Jan 31 | 2022-01-31 00:00:00 UTC | 2022-02-07 00:00:00 UTC | 0 | 0 | 0 |
| Feb 7 | 2022-02-07 00:00:00 UTC | 2022-02-14 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
4 sourcesWe fine-tuned the model on a dozens of different NLP datasets and tasks in a prompted style. You can read all the prompts in the appendix or get them all here: https://github.com/bigscience-workshop/promptsource . Most NLP tasks are not particularly freeform, or they are naturally length limited like summary (XSum is very short). As a consequence, the model mostly defaults to short responses. Your "trick" is not that unreasonable though! Many of the training prompts that want long responses, ask for them explicitly.
In T0* – Series of encoder-decoder models trained on a large set of different tasksArXiv link to the paper: https://arxiv.org/abs/2110.08207
GitHub repo: https://github.com/bigscience-workshop/promptsource
In T0* – Series of encoder-decoder models trained on a large set of different tasks