deepspeed_testing
text-to-text-transfer-transformer
| deepspeed_testing | text-to-text-transfer-transformer | |
|---|---|---|
| 1 | 29 | |
| 0 | 5,972 | |
| - | 1.1% | |
| 2.7 | 3.6 | |
| about 3 years ago | 4 days ago | |
| Shell | Python | |
| - | 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.
deepspeed_testing
-
DeepSpeed Investigation: What I Learned
To test out DeepSpeed, I used the awesome HuggingFace transformers library, which supports using DeepSpeed on their non-stable branch (though support is coming to the stable branch in 4.6 🤓). I followed these awesome instructions on the HuggingFace’s website for getting started with DeepSpeed and HuggingFace. If you want to follow along at home, I created a Github repository with the Dockerfile (I’m addicted to docker and will probably make a blog post on docker too :)) and the test script I used to run my experiments on. I tried training the different versions of the awesome T5 model that ranged from smallish ~60 million parameters to humungous 3 billion parameters. And here are my results:
text-to-text-transfer-transformer
- T5: Text-to-Text-Transfer-Transformer
-
Gemma: New Open Models
Google released the T5 paper about 5 years ago:
https://arxiv.org/abs/1910.10683
This included full model weights along with a detailed description of the dataset, training process, and ablations that led them to that architecture. T5 was state-of-the-art on many benchmarks when it was released, but it was of course quickly eclipsed by GPT-3.
Following GPT-3, it became much more common for labs to not release full details or model weights. Prior to that, it was common practice from Google (BERT, T5), Meta (BART), OpenAI (GPT1, GPT2) and others to release full training details and model weights.
-
[P] Free and Fast LLM Finetuning
[2] - https://arxiv.org/abs/1910.10683
- Free and Fast LLM Finetuning
-
[Discussion] Is there a better way than positional encodings in self attention?
T5-style relative encodings https://arxiv.org/abs/1910.10683
-
What were the 40 research papers on the list Ilya Sutskever gave John Carmack?
11. T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer" (2020) - https://arxiv.org/abs/1910.10683 (Google Research)
-
[P] T5 Implementation in PyTorch
You can find a link to the paper here: https://arxiv.org/abs/1910.10683
-
Text-to-Text Transformer (T5-Base Model) Testing For Summarization, Sentiment Classification, and Translation Using Pytorch and Torchtext
The Text-to-Text Transformer is a type of neural network architecture that is particularly well-suited for natural language processing tasks involving the generation of text. It was introduced in the paper "Attention is All You Need" by Vaswani et al. and has since become a popular choice for many NLP tasks, including language translation, summarization, and text generation
- AlphaCode by DeepMind
-
[R] LiBai: a large-scale open-source model training toolbox
Found relevant code at https://github.com/google-research/text-to-text-transfer-transformer + all code implementations here
What are some alternatives?
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
DeepCreamPy - Decensoring Hentai with Deep Neural Networks
dalle-mini - DALL·E Mini - Generate images from a text prompt
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
majesty-diffusion - Majesty Diffusion by @Dango233(@Dango233max) and @apolinario (@multimodalart)
nlu - 1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
text-to-text-transfer-tra
imagen-pytorch - Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
hent-AI - Automation of censor bar detection
DeepCreamPy - deeppomf's DeepCreamPy + some updates