MAmatco11·Feb 22, 2023Submission
Microsoft bioGPT: pre-trained transformer for biomedical text
3 points · Open discussionmicrosoft
BioGPT
Python2023–2023
microsoft / BioGPT · Archived
BioGPT
Discover this repository through its Hacker News conversations.
6Distinct people
6Mentions
0Explicit recommenders
4.5KGitHub stars
What to know before exploring
What it is
A public description has not been verified.
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, 3:03:16 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 day6 dated mentions
Observed mentions: 2023-02-01 13:36:49 UTC to 2023-02-22 10:43:50 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 |
|---|---|---|---|---|---|
| Feb 1 | 2023-02-01 00:00:00 UTC | 2023-02-02 00:00:00 UTC | 3 | 1 | 2 |
| Feb 2 | 2023-02-02 00:00:00 UTC | 2023-02-03 00:00:00 UTC | 1 | 0 | 1 |
| Feb 3 | 2023-02-03 00:00:00 UTC | 2023-02-04 00:00:00 UTC | 0 | 0 | 0 |
| Feb 4 | 2023-02-04 00:00:00 UTC | 2023-02-05 00:00:00 UTC | 0 | 0 | 0 |
| Feb 5 | 2023-02-05 00:00:00 UTC | 2023-02-06 00:00:00 UTC | 0 | 0 | 0 |
| Feb 6 | 2023-02-06 00:00:00 UTC | 2023-02-07 00:00:00 UTC | 0 | 0 | 0 |
| Feb 7 | 2023-02-07 00:00:00 UTC | 2023-02-08 00:00:00 UTC | 0 | 0 | 0 |
| Feb 8 | 2023-02-08 00:00:00 UTC | 2023-02-09 00:00:00 UTC | 0 | 0 | 0 |
| Feb 9 | 2023-02-09 00:00:00 UTC | 2023-02-10 00:00:00 UTC | 0 | 0 | 0 |
| Feb 10 | 2023-02-10 00:00:00 UTC | 2023-02-11 00:00:00 UTC | 1 | 1 | 0 |
| Feb 11 | 2023-02-11 00:00:00 UTC | 2023-02-12 00:00:00 UTC | 0 | 0 | 0 |
| Feb 12 | 2023-02-12 00:00:00 UTC | 2023-02-13 00:00:00 UTC | 0 | 0 | 0 |
| Feb 13 | 2023-02-13 00:00:00 UTC | 2023-02-14 00:00:00 UTC | 0 | 0 | 0 |
| Feb 14 | 2023-02-14 00:00:00 UTC | 2023-02-15 00:00:00 UTC | 0 | 0 | 0 |
| Feb 15 | 2023-02-15 00:00:00 UTC | 2023-02-16 00:00:00 UTC | 0 | 0 | 0 |
| Feb 16 | 2023-02-16 00:00:00 UTC | 2023-02-17 00:00:00 UTC | 0 | 0 | 0 |
| Feb 17 | 2023-02-17 00:00:00 UTC | 2023-02-18 00:00:00 UTC | 0 | 0 | 0 |
| Feb 18 | 2023-02-18 00:00:00 UTC | 2023-02-19 00:00:00 UTC | 0 | 0 | 0 |
| Feb 19 | 2023-02-19 00:00:00 UTC | 2023-02-20 00:00:00 UTC | 0 | 0 | 0 |
| Feb 20 | 2023-02-20 00:00:00 UTC | 2023-02-21 00:00:00 UTC | 0 | 0 | 0 |
| Feb 21 | 2023-02-21 00:00:00 UTC | 2023-02-22 00:00:00 UTC | 0 | 0 | 0 |
| Feb 22 | 2023-02-22 00:00:00 UTC | 2023-02-23 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
6 sourcesThis model looks much too small to be effective. They announced an open model of 1.5B parameters [0] coming soon. Contrast this with davinci-003 or BigScience BLOOM, both with ~176 params.
I don't see how this will generate text that is comprehensive or useful. The open GPT models of that size aren't useable for text generation for anything serious. Adding the sensitivity of health/clinical I'd steer clear of this. Even BLOOM's model card specifically calls out biomedical as a misuse of the model [1].
[0] https://github.com/microsoft/BioGPT#news
[1] See "Out-of-scope" in https://huggingface.co/bigscience/bloom
In BioGPT: A language model pre-trained on large-scale biomedical literatureBioGPT: Generative Pre-Trained Transformer for Biomedical Text Generation
1 points · Open discussionYou can't (yet). But there are pretty detailed instructions on how to get started with the model here https://github.com/microsoft/BioGPT
In BioGPT: A language model pre-trained on large-scale biomedical literature