Difference between revisions of "Free Software Directory:Artificial Intelligence Team"
m |
m (Transformer-based Language Model) |
||
| Line 6: | Line 6: | ||
** Speech synthesis (text to speech (TTS)) | ** Speech synthesis (text to speech (TTS)) | ||
*** [[Coqui]] | *** [[Coqui]] | ||
| − | * Text generation: | + | * Text generation, Transformer-based Language Model: |
** [[GPT-Neo]] | ** [[GPT-Neo]] | ||
*** "*As of August, 2021 code is no longer maintained. It is preserved here in archival form for people who wish to continue to use it." - https://github.com/EleutherAI/gpt-neo | *** "*As of August, 2021 code is no longer maintained. It is preserved here in archival form for people who wish to continue to use it." - https://github.com/EleutherAI/gpt-neo | ||
Revision as of 22:30, 24 February 2023
- Argos Translate
- Text/speech
- Text generation, Transformer-based Language Model:
- GPT-Neo
- "*As of August, 2021 code is no longer maintained. It is preserved here in archival form for people who wish to continue to use it." - https://github.com/EleutherAI/gpt-neo
- Still useful since it's lightweight hardware requirement
- Usage: Install transformers (search "Transformers" in this page) and then run the little three line code snippet on https://huggingface.co/EleutherAI/gpt-neo-125M
- GPT-J
- "To load GPT-J in float32 one would need at least 2x model size CPU RAM: 1x for initial weights and another 1x to load the checkpoint. So for GPT-J it would take at least 48GB of CPU RAM to just load the model." - https://huggingface.co/docs/transformers/v4.14.1/en/model_doc/gptj
- EleutherAI: GPT-NeoX
- "Basically GPT-NeoX requires at least 42GB of VRAM and 40 GB of disk space (and yes we're talking about the slim fp16 version here)." - https://nlpcloud.com/deploying-gpt-neox-20-production-focus-deepspeed.html
- GPT-Neo
- Image creation:
- Package manager: Transformers - https://github.com/huggingface/transformers/
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the page “GNU Free Documentation License”.
The copyright and license notices on this page only apply to the text on this page. Any software or copyright-licenses or other similar notices described in this text has its own copyright notice and license, which can usually be found in the distribution or license text itself.