PYpyinstallwoes·Dec 18, 2023Submission
Embed arbitrary modalities (images, audio, documents, etc.) into LLMs
2 points · Open discussionsshh12
multi_token
Python2023–2023
sshh12 / multi_token
multi_token
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
2Distinct people
2Mentions
0Explicit recommenders
187GitHub stars
What to know before exploring
What it is
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
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 day2 dated mentions
Observed mentions: 2023-12-05 17:00:29 UTC to 2023-12-18 09:01:17 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 |
|---|---|---|---|---|---|
| Dec 5 | 2023-12-05 00:00:00 UTC | 2023-12-06 00:00:00 UTC | 1 | 0 | 1 |
| Dec 6 | 2023-12-06 00:00:00 UTC | 2023-12-07 00:00:00 UTC | 0 | 0 | 0 |
| Dec 7 | 2023-12-07 00:00:00 UTC | 2023-12-08 00:00:00 UTC | 0 | 0 | 0 |
| Dec 8 | 2023-12-08 00:00:00 UTC | 2023-12-09 00:00:00 UTC | 0 | 0 | 0 |
| Dec 9 | 2023-12-09 00:00:00 UTC | 2023-12-10 00:00:00 UTC | 0 | 0 | 0 |
| Dec 10 | 2023-12-10 00:00:00 UTC | 2023-12-11 00:00:00 UTC | 0 | 0 | 0 |
| Dec 11 | 2023-12-11 00:00:00 UTC | 2023-12-12 00:00:00 UTC | 0 | 0 | 0 |
| Dec 12 | 2023-12-12 00:00:00 UTC | 2023-12-13 00:00:00 UTC | 0 | 0 | 0 |
| Dec 13 | 2023-12-13 00:00:00 UTC | 2023-12-14 00:00:00 UTC | 0 | 0 | 0 |
| Dec 14 | 2023-12-14 00:00:00 UTC | 2023-12-15 00:00:00 UTC | 0 | 0 | 0 |
| Dec 15 | 2023-12-15 00:00:00 UTC | 2023-12-16 00:00:00 UTC | 0 | 0 | 0 |
| Dec 16 | 2023-12-16 00:00:00 UTC | 2023-12-17 00:00:00 UTC | 0 | 0 | 0 |
| Dec 17 | 2023-12-17 00:00:00 UTC | 2023-12-18 00:00:00 UTC | 0 | 0 | 0 |
| Dec 18 | 2023-12-18 00:00:00 UTC | 2023-12-19 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
2 sourcesThese sentiments are pretty close to my own. I read a paper that claimed that llms are General Pattern Machines and could be used to complete small games in gym environments. It seems to me that if these things really are General Pattern Machines all we have to do is figure out a way to represent any data as a pattern and try and predict the next step in the pattern right?
The multi token[1] project which allows you to take any type of data and turn it into a token it's pretty interesting and seems like it's going in this direction.
I would really like to see a framework where you can take any modality of any type turn it into a series of tokens and just cram it into a language model and effectively turning into a multimodal model with almost no effort.
[0]https://general-pattern-machines.github.io/
[1] https://github.com/sshh12/multi_tok