fairseq
gpt-neox
Our great sponsors
| fairseq | gpt-neox | |
|---|---|---|
| 89 | 52 | |
| 29,160 | 6,532 | |
| 1.4% | 1.6% | |
| 6.6 | 9.0 | |
| 7 days ago | 6 days ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
fairseq
- Unsupervised (Semi-Supervised) ASR/STT training recipes
-
Voice generation AI (TTS)
It might be worth checking out Meta's TTS tho, I haven't gotten the chance to fiddle around with it but it looks somewhat promising https://github.com/facebookresearch/fairseq/tree/main/examples/mms
-
Translation app with TTS (text-to-speech) for Persian?
META's mms supports tts for Persian according to https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html
They have instructions on how to use it in command line and a notebook on how to use it as a python library.
- Why no work on open source TTS (Text to speech) models
-
AI — weekly megathread!
Meta released a new open-source model, Massively Multilingual Speech (MMS) that can do both speech-to-text and text-to-speech in 1,107 languages and can also recognize 4,000+ spoken languages. Existing speech recognition models only cover approximately 100 languages out of the 7,000+ known spoken languages. [Details | Research Paper | GitHub].
- Massively Multilingual Search - Speech to Text and Text to Speech in 1,100+ Languages (open source, Meta)
-
Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
Code: https://github.com/facebookresearch/fairseq/tree/main/examples/mms
-
Why is GPT-3 15.77x more expensive for certain languages?
https://github.com/facebookresearch/fairseq/blob/nllb/LICENS...
The model is CC. Because models aren't software.
gpt-neox
- FLaNK Stack 26 February 2024
-
Read this post if you have general questions
GPT-Neo: GPT-Neo is a free and open-source language model developed by EleutherAI. It is a powerful model that can be used for a variety of tasks, including text generation, and question-answering. here is the GitHub
-
What's the current state of actually free and open source LLMs?
Doesn't gpt-neox 20b require like 40gb+ of VRAM? From their github repo the slim weights are 39GB and I think one of the devs has previously mentioned aiming for 48GB for inference.
-
Any real competitor to GPT-3 which is open source and downloadable?
3.) EleutherAI's GPT-Neo and GPT-NeoX: EleutherAI is an independent research organization that aims to promote open research in artificial intelligence. They have released GPT-Neo, an open-source language model based on the GPT architecture, and are developing GPT-NeoX, a highly-scalable GPT-like model. You can find more information on their GitHub repositories: GPT-Neo: https://github.com/EleutherAI/gpt-neo GPT-NeoX: https://github.com/EleutherAI/gpt-neox
- Behold, ChatGPT from the year 2025
-
Will there ever be a "Stable Diffusion chat AI" that we can run at home like one can do with Stable Diffusion? A "roll-your-own at home ChatGPT"?
GitHub - EleutherAI/gpt-neox: An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
-
First Open Source Alternative to ChatGPT Has Arrived
For context, they're now working on a GPU driven version:
-
Will we see a “stable diffusion” version of ChatGPT?
freediver 2 days ago | prev | next [–] Here is an example of one general purpose open source LLM, probably the best you can get: https://github.com/EleutherAI/gpt-neox To manage your expectations it is nowhere as good as ChatGPT. If you are interested in programming only: https://github.com/salesforce/CodeGen
- GPT-3 can create both sides of an Interactive Fiction transcript
-
[D] Is a GPT-J successor in the works?
There's been a few different open-source GPT-3 style large language models since GPT-J: ~175B: Bloom from huggingface, ~100B: YaLM from Yandex, and ~20B: GPT NeoX. None of them match GPT-3 performance but since their open source (for commercial use too) theyre worth checking out. I'm not sure if Stability has plans to train a GPT3 size model though.
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
gpt-neo - An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
text-to-text-transfer-transformer - Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
espnet - End-to-End Speech Processing Toolkit
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
YaLM-100B - Pretrained language model with 100B parameters
open-ai - OpenAI PHP SDK : Most downloaded, forked, contributed, huge community supported, and used PHP (Laravel , Symfony, Yii, Cake PHP or any PHP framework) SDK for OpenAI GPT-3 and DALL-E. It also supports chatGPT-like streaming. (ChatGPT AI is supported)
lm-evaluation-harness - A framework for few-shot evaluation of language models.
Megatron-DeepSpeed - Ongoing research training transformer language models at scale, including: BERT & GPT-2
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.