Difference between revisions of "Free Software Directory:Artificial Intelligence Team"

From Free Software Directory
Jump to: navigation, search
m (table formatting and fixing some ordering)
m (added neat looking agnai project (multiple character chatbot))
(2 intermediate revisions by the same user not shown)
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/EleutherAI/gpt-neox GPT-NeoX]  
+
! [https://github.com/agnaistic/agnai Agnai]
−
| EleutherAI
+
| agnaistic
−
| [https://github.com/EleutherAI/gpt-neox/blob/main/LICENSE Apache 2.0]
+
| [https://github.com/agnaistic/agnai#AGPL-3.0-1-ov-file AGPLv3]
 +
| AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.
 +
|-
 +
! [https://github.com/turboderp/exllamav2 ExLlamaV2]
 +
| turboderp
 +
| [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://github.com/LAION-AI/Open-Assistant Open Assistant]  
+
! [https://github.com/LostRuins/koboldcpp koboldcpp]  
−
| LAION-AI 
+
| LostRuins
−
| [https://github.com/LAION-AI/Open-Assistant/blob/main/LICENSE Apache 2.0]
+
| [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/KillianLucas/open-interpreter Open Interpreter]  
+
! [https://github.com/serge-chat/serge Serge]  
−
| KillianLucas
+
| serge-chat
−
| [https://github.com/KillianLucas/open-interpreter/blob/main/LICENSE MIT]
+
| [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/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/stability-AI/stableLM/ StableLM]
 
−
| Stability AI
 
−
| [https://github.com/Stability-AI/StableLM/blob/main/LICENSE Apache 2.0]
 
 
|-
 
|-
 
! [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
 
|-
 
|-
−
! [https://github.com/wawawario2/long_term_memory Text Generation Web UI with Long-Term Memory] 
 
−
| wawawario2
 
−
| [https://github.com/wawawario2/long_term_memory/blob/master/LICENSE AGPLv3]
 
 
|}
 
|}
−
{| class="wikitable sortable"
+
 
−
|+ LLaMA-based
+
====Models====
 +
{| class="wikitable sortable"  
 
|-
 
|-
 
! Project  
 
! Project  
 
! Credit  
 
! Credit  
 
! License
 
! License
 +
! Description
 
|-
 
|-
−
! [https://github.com/AmineDiro/cria cria - LLaMA ported to Rust]  
+
! [https://github.com/ggerganov/llama.cpp llama.cpp]
−
| AmineDiro
+
| ggerganov (Georgi Gerganov)
−
| [https://github.com/AmineDiro/cria/blob/main/LICENSE MIT]
+
| [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://github.com/lm-sys/FastChat FastChat]  
+
! [https://mistral.ai/news/mixtral-of-experts/ Mixtral]
−
| lm-sys
+
| Mistral AI
−
| [https://github.com/lm-sys/FastChat/blob/main/LICENSE Apache-2.0]
+
| [https://docs.mistral.ai/ Apache 2.0]
 +
| Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference.
 
|-
 
|-
−
! [https://github.com/nomic-ai/gpt4all GPT4All]
+
|}
−
| Nomic AI
+
====Other====
−
| [https://github.com/nomic-ai/gpt4all/blob/main/LICENSE.txt MIT]
+
{| class="wikitable sortable"
 
|-
 
|-
−
! [https://github.com/LostRuins/koboldcpp koboldcpp]
+
! Project
−
| LostRuins
+
! Credit
−
| [https://github.com/LostRuins/koboldcpp/blob/concedo/LICENSE.md AGPLv3]
+
! License
 +
! Description
 
|-
 
|-
−
! [https://github.com/facebookresearch/llama LLaMA] [[LLaMA|FSD]]  
+
! [https://github.com/EleutherAI/gpt-neox GPT-NeoX]  
−
| Meta Research
+
| EleutherAI
−
| [https://github.com/facebookresearch/llama/blob/main/LICENSE GPLv3]
+
| [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/ggerganov/llama.cpp LLaMA ported to C/C++] [[LLaMA.cpp|FSD]]  
+
! [https://github.com/lm-sys/FastChat FastChat]  
−
| ggerganov (Georgi Gerganov)
+
| lm-sys
−
| [https://github.com/ggerganov/llama.cpp/blob/master/LICENSE MIT]
+
| [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/artidoro/qlora QLoRA]  
+
! [https://github.com/LAION-AI/Open-Assistant Open Assistant]  
−
| artidoro
+
| LAION-AI 
−
| [https://github.com/artidoro/qlora/blob/main/LICENSE.txt MIT]
+
| [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/serge-chat/serge Serge]  
+
! [https://github.com/KillianLucas/open-interpreter Open Interpreter]  
−
| serge-chat
+
| KillianLucas
−
| [https://github.com/serge-chat/serge/blob/main/LICENSE MIT]
+
| [https://github.com/KillianLucas/open-interpreter/blob/main/LICENSE AGPLv3]
 +
| Lets LLMs run code (Python, Javascript, Shell, and more) locally.
 
|-
 
|-
−
! [https://github.com/nlpxucan/WizardLM WizardLM]
 
−
| nlpxucan
 
−
| [https://github.com/nlpxucan/WizardLM/blob/main/README.md Apache-2.0]
 
 
|}
 
|}
 +
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 163: Line 191:
 
== Images ==
 
== Images ==
 
=== Image generation ===
 
=== Image generation ===
 +
==== Text to image ====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
Line 196: Line 225:
 
| 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 204: Line 263:
 
| 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 23:47, 22 February 2024

Free Software Foundation-Free Software Directory-Artificial Intelligence Project Team.png

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

Transformers

Text

Grammar

Translation

Text generation

Front ends

Project Credit License Description
Agnai agnaistic AGPLv3 AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.
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.

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

3D modeling

Audio

Natural language processing (NLP)

Transcription (Speech to text (STT))

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


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.

Retrieved from "https://directory.fsf.org/wiki?title=Free_Software_Directory:Artificial_Intelligence_Team&oldid=90808"