Difference between revisions of "Free Software Directory:Artificial Intelligence Team"
GrahamxReed (talk | contribs) (Updating Text Gens: Added mixtral, removed LLaMA link due to having new strange license + added web archive link to clarify GG port was AGPLv3 -> MIT, removed aminediro because it only supports/enables nonfree license usage) |
GrahamxReed (talk | contribs) (Adding video generation. Organized text generation.) |
||
Line 71: | Line 71: | ||
=== Text generation === | === Text generation === | ||
+ | ====Front ends==== | ||
{| class="wikitable sortable" | {| class="wikitable sortable" | ||
|- | |- | ||
Line 76: | Line 77: | ||
! Credit | ! Credit | ||
! License | ! License | ||
+ | ! Description | ||
|- | |- | ||
− | ! | + | ! [https://github.com/turboderp/exllamav2 ExLlamaV2] |
− | | | + | | turboderp |
− | | [https://github.com/ | + | | [https://github.com/turboderp/exllamav2?tab=MIT-1-ov-file#readme MIT License] |
+ | | A fast inference library for running LLMs locally on modern consumer-class GPUs | ||
+ | |- | ||
+ | ! [https://github.com/turboderp/exui ExLlamaV2 WebUI] | ||
+ | | turboderp | ||
+ | | [https://github.com/turboderp/exui?tab=MIT-1-ov-file#readme MIT License] | ||
+ | | | ||
+ | |- | ||
+ | ! [https://github.com/nomic-ai/gpt4all GPT4All] | ||
+ | | Nomic AI | ||
+ | | [https://github.com/nomic-ai/gpt4all/blob/main/LICENSE.txt MIT] | ||
+ | | Run open-source LLMs anywhere | ||
|- | |- | ||
! [https://github.com/KoboldAI/KoboldAI-Client KoboldAI] | ! [https://github.com/KoboldAI/KoboldAI-Client KoboldAI] | ||
| KoboldAI | | KoboldAI | ||
| [https://github.com/KoboldAI/KoboldAI-Client/blob/main/LICENSE.md AGPLv3] | | [https://github.com/KoboldAI/KoboldAI-Client/blob/main/LICENSE.md AGPLv3] | ||
+ | | A browser-based front-end for AI-assisted writing with multiple local & remote AI models | ||
|- | |- | ||
− | ! [https:// | + | ! [https://github.com/LostRuins/koboldcpp koboldcpp] |
− | | | + | | LostRuins |
− | | [https:// | + | | [https://github.com/LostRuins/koboldcpp/blob/concedo/LICENSE.md AGPLv3] |
+ | | A simple one-file way to run various GGML and GGUF models with KoboldAI's UI | ||
|- | |- | ||
− | + | ! [https://github.com/serge-chat/serge Serge] | |
− | + | | serge-chat | |
− | + | | [https://github.com/serge-chat/serge/blob/main/LICENSE MIT] | |
− | + | | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API. | |
− | ! [https://github.com/ | ||
− | | | ||
− | | [https://github.com/ | ||
− | | | ||
− | |||
− | |||
− | |||
|- | |- | ||
! [https://github.com/SillyTavern/SillyTavern SillyTavern] | ! [https://github.com/SillyTavern/SillyTavern SillyTavern] | ||
| SillyTavern | | SillyTavern | ||
| [https://github.com/SillyTavern/SillyTavern/blob/release/LICENSE AGPLv3] | | [https://github.com/SillyTavern/SillyTavern/blob/release/LICENSE AGPLv3] | ||
− | | | + | | LLM Frontend for Power Users |
− | |||
− | |||
− | |||
|- | |- | ||
! [https://github.com/oobabooga/text-generation-webui Text Generation Web UI] | ! [https://github.com/oobabooga/text-generation-webui Text Generation Web UI] | ||
| oobabooga | | oobabooga | ||
| [https://github.com/oobabooga/text-generation-webui/blob/main/LICENSE AGPLv3] | | [https://github.com/oobabooga/text-generation-webui/blob/main/LICENSE AGPLv3] | ||
+ | | A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models | ||
+ | |- | ||
+ | |} | ||
+ | |||
+ | ====Models==== | ||
+ | {| class="wikitable sortable" | ||
+ | |- | ||
+ | ! Project | ||
+ | ! Credit | ||
+ | ! License | ||
+ | ! Description | ||
+ | |- | ||
+ | ! [https://github.com/ggerganov/llama.cpp llama.cpp] | ||
+ | | ggerganov (Georgi Gerganov) | ||
+ | | [https://github.com/ggerganov/llama.cpp/blob/master/LICENSE MIT] | ||
+ | | Port of Facebook's LLaMA model in C/C++ | ||
+ | |- | ||
+ | ! [https://mistral.ai/news/announcing-mistral-7b/ Mistral] | ||
+ | | Mistral AI | ||
+ | | [https://docs.mistral.ai/ Apache 2.0] | ||
+ | | Mistral 7B significantly outperforms Llama 2 13B on all metrics, and is on par with Llama 34B. | ||
+ | |- | ||
+ | ! [https://mistral.ai/news/mixtral-of-experts/ Mixtral] | ||
+ | | Mistral AI | ||
+ | | [https://docs.mistral.ai/ Apache 2.0] | ||
+ | | Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. | ||
|- | |- | ||
|} | |} | ||
− | {| class="wikitable sortable" | + | ====Other==== |
− | + | {| class="wikitable sortable" | |
|- | |- | ||
! Project | ! Project | ||
! Credit | ! Credit | ||
! License | ! License | ||
+ | ! Description | ||
+ | |- | ||
+ | ! [https://github.com/EleutherAI/gpt-neox GPT-NeoX] | ||
+ | | EleutherAI | ||
+ | | [https://github.com/EleutherAI/gpt-neox/blob/main/LICENSE Apache 2.0] | ||
+ | | EleutherAI's library for training large-scale language models on GPUs | ||
|- | |- | ||
! [https://github.com/lm-sys/FastChat FastChat] | ! [https://github.com/lm-sys/FastChat FastChat] | ||
| lm-sys | | lm-sys | ||
| [https://github.com/lm-sys/FastChat/blob/main/LICENSE Apache-2.0] | | [https://github.com/lm-sys/FastChat/blob/main/LICENSE Apache-2.0] | ||
+ | | An open platform for training, serving, and evaluating large language models. | ||
|- | |- | ||
− | ! [https://github.com/ | + | ! [https://github.com/LAION-AI/Open-Assistant Open Assistant] |
− | | | + | | LAION-AI |
− | | [https://github.com/ | + | | [https://github.com/LAION-AI/Open-Assistant/blob/main/LICENSE Apache 2.0] |
+ | | A chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so | ||
|- | |- | ||
− | ! [https://github.com/ | + | ! [https://github.com/KillianLucas/open-interpreter Open Interpreter] |
− | | | + | | KillianLucas |
− | | [https://github.com/ | + | | [https://github.com/KillianLucas/open-interpreter/blob/main/LICENSE AGPLv3] |
− | | | + | | Lets LLMs run code (Python, Javascript, Shell, and more) locally. |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|- | |- | ||
− | |||
− | |||
− | |||
|} | |} | ||
+ | Honorary mention: LLaMA 1 had an [http://web.archive.org/web/20230224201551/https://github.com/facebookresearch/llama/blob/main/LICENSE AGPLv3] license. | ||
=== Code generation === | === Code generation === | ||
Line 160: | Line 186: | ||
== Images == | == Images == | ||
=== Image generation === | === Image generation === | ||
+ | ==== Text to image ==== | ||
{| class="wikitable sortable" | {| class="wikitable sortable" | ||
|- | |- | ||
Line 193: | Line 220: | ||
| AUTOMATIC1111 | | AUTOMATIC1111 | ||
| [https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/LICENSE.txt AGPLv3] | | [https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/LICENSE.txt AGPLv3] | ||
+ | |- | ||
+ | |} | ||
+ | |||
+ | ====Videos==== | ||
+ | Image generation techniques create pictures from noise estimations. This noise shows up as artifacts and hampers temporal stability for objects. These projects tackle that issue. | ||
+ | {| class="wikitable sortable" | ||
+ | |- | ||
+ | ! Project | ||
+ | ! Credit | ||
+ | ! License | ||
+ | |- | ||
+ | ! [https://github.com/google-research/frame-interpolation FILM: Frame Interpolation for Large Motion] | ||
+ | | Google Research | ||
+ | | [https://github.com/google-research/frame-interpolation#Apache-2.0-1-ov-file Apache 2.0] | ||
+ | |- | ||
+ | ! [https://github.com/magic-research/magic-animate MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model] | ||
+ | | MagIC Research | ||
+ | | [https://github.com/magic-research/magic-animate#BSD-3-Clause-1-ov-file BSD-3-Clause license] | ||
+ | |- | ||
+ | ! [https://github.com/TencentARC/MotionCtrl MotionCtrl: A Unified and Flexible Motion Controller for Video Generation] | ||
+ | | ARC Lab, Tencent PCG | ||
+ | | [https://github.com/TencentARC/MotionCtrl#Apache-2.0-1-ov-file Apache 2.0] | ||
+ | |- | ||
+ | ! [https://stability.ai/news/stable-video-diffusion-open-ai-video-model Stable Video Diffusion] | ||
+ | | Stability AI | ||
+ | | [https://github.com/Stability-AI/generative-models#MIT-1-ov-file MIT License] | ||
+ | |- | ||
+ | ! [https://github.com/CiaraStrawberry/TemporalKit TemporalKit] | ||
+ | | CiaraStrawberry (Ciara Rowles) | ||
+ | | [https://github.com/CiaraStrawberry/TemporalKit?tab=GPL-3.0-1-ov-file#readme GPLv3] | ||
|- | |- | ||
! [https://github.com/camenduru/text-to-video-synthesis-colab Text To Video Synthesis Colab] | ! [https://github.com/camenduru/text-to-video-synthesis-colab Text To Video Synthesis Colab] | ||
Line 201: | Line 258: | ||
| yoyo-nb | | yoyo-nb | ||
| [https://github.com/yoyo-nb/Thin-Plate-Spline-Motion-Model/blob/main/LICENSE MIT] | | [https://github.com/yoyo-nb/Thin-Plate-Spline-Motion-Model/blob/main/LICENSE MIT] | ||
+ | |- | ||
|} | |} | ||
+ | |||
+ | |||
=== Image captioning === | === Image captioning === |
Revision as of 22:28, 22 February 2024
The Artificial Intelligence Project Team gathers free software resources regarding machine learning / artificial intelligence.
Group info | User info | |||||
---|---|---|---|---|---|---|
User | Role | Reference | Real name | libera.chat nick | Time zone | Title |
David_Hedlund | Coordinator | David Hedlund | David_Hedlund | Europe/Stockholm | ||
GrahamxReed | Collaborator | Graham Reed | Graham_Reed | America/New_York | ||
Mertgor | Observer | Mert Gör | hwpplayer1 | Europe/Istanbul | ||
Mmcmahon | Team captain | Michael McMahon | thomzane | America/New_York | FSF Systems Administrator |
Truthfulness
- US NIST AI Risk Management Framework Playbook
- A science paper benchmark: TruthfulQA: Measuring How Models Mimic Human Falsehoods
Transformers
- Package manager and player: Transformers - https://github.com/huggingface/transformers/
- Original science paper: Attention Is All You Need
Text
Grammar
Translation
Text generation
Front ends
Project | Credit | License | Description |
---|---|---|---|
ExLlamaV2 | turboderp | MIT License | A fast inference library for running LLMs locally on modern consumer-class GPUs |
ExLlamaV2 WebUI | turboderp | MIT License | |
GPT4All | Nomic AI | MIT | Run open-source LLMs anywhere |
KoboldAI | KoboldAI | AGPLv3 | A browser-based front-end for AI-assisted writing with multiple local & remote AI models |
koboldcpp | LostRuins | AGPLv3 | A simple one-file way to run various GGML and GGUF models with KoboldAI's UI |
Serge | serge-chat | MIT | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API. |
SillyTavern | SillyTavern | AGPLv3 | LLM Frontend for Power Users |
Text Generation Web UI | oobabooga | AGPLv3 | A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models |
Models
Project | Credit | License | Description |
---|---|---|---|
llama.cpp | ggerganov (Georgi Gerganov) | MIT | Port of Facebook's LLaMA model in C/C++ |
Mistral | Mistral AI | Apache 2.0 | Mistral 7B significantly outperforms Llama 2 13B on all metrics, and is on par with Llama 34B. |
Mixtral | Mistral AI | Apache 2.0 | Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. |
Other
Project | Credit | License | Description |
---|---|---|---|
GPT-NeoX | EleutherAI | Apache 2.0 | EleutherAI's library for training large-scale language models on GPUs |
FastChat | lm-sys | Apache-2.0 | An open platform for training, serving, and evaluating large language models. |
Open Assistant | LAION-AI | Apache 2.0 | A chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so |
Open Interpreter | KillianLucas | AGPLv3 | Lets LLMs run code (Python, Javascript, Shell, and more) locally. |
Honorary mention: LLaMA 1 had an AGPLv3 license.
Code generation
This concept is controversial. See the FSF's other writing on this topic.
- CodeGen by Salesforce FSD | BSD 3-Clause "New" or "Revised" License
- TurboPilot by ravenscroftj (James Ravenscroft) FSD | BSD 3-Clause "New" or "Revised" License
- CodeGen2 by Salesforce FSD | Apache-2.0
Images
Image generation
Text to image
Project | Credit | License |
---|---|---|
ComfyUI | comfyanonymous | GPLv3 |
ControlNet | lllyasviel | Apache-2.0 |
DALL-E Mini | borisdayma (Boris Dayma) | Apache 2.0 |
Diffusers | huggingface | Apache-2.0 |
neural-style | anishathalye | GPLv3 |
SDXL - generative-models | Stability-AI | MIT |
Stable Diffusion WebUI | AUTOMATIC1111 | AGPLv3 |
Videos
Image generation techniques create pictures from noise estimations. This noise shows up as artifacts and hampers temporal stability for objects. These projects tackle that issue.
Project | Credit | License |
---|---|---|
FILM: Frame Interpolation for Large Motion | Google Research | Apache 2.0 |
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model | MagIC Research | BSD-3-Clause license |
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation | ARC Lab, Tencent PCG | Apache 2.0 |
Stable Video Diffusion | Stability AI | MIT License |
TemporalKit | CiaraStrawberry (Ciara Rowles) | GPLv3 |
Text To Video Synthesis Colab | camenduru | The Unlicense |
Thin-Plate Spline Motion Model for Image Animation | yoyo-nb | MIT |
Image captioning
- MiniGPT-4 by Vision-CAIR | BSD 3-Clause "New" or "Revised" License & BSD 3-Clause License
- LLaVA by Haotian Liu | Apache License 2.0
3D modeling
Audio
Natural language processing (NLP)
Transcription (Speech to text (STT))
- Vosk
- Whisper
- OpenAI's Whisper model ported to C/C++ by ggerganov (Georgi Gerganov) | MIT License
Speech synthesis (text to speech (TTS))
Project | Credit | License |
---|---|---|
Bark | Suno AI | MIT License |
Coqui TTS | Coqui AI | MPL 2.0 |
SoftVC VITS Singing Voice Conversion Fork | voicepaw | Apache License 2.0 & MIT License |
TorToiSe | neonbjb (James Betker) | Apache License 2.0 |
Music
- Moseca separates music tracks into different stems (voice, drums, bass, guitar, piano, and others). This is useful for remixing, karaoke, and music studies. MIT
Uncategorized
- Virtual assistant: Mycroft
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.