tf-transformers
transformers
Our great sponsors
tf-transformers | transformers | |
---|---|---|
5 | 175 | |
84 | 125,021 | |
- | 3.1% | |
1.7 | 10.0 | |
about 1 year ago | 3 days ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | 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.
tf-transformers
-
Tensorflow-Transformers 2.0 ( for NLP, CV, Audio )
Code : GitHub - legacyai/tf-transformers: State of the art faster Natural Language Processing in Tensorflow 2.0 . 1 Website : https://legacyai.github.io/tf-transformers 1
- [P] Production Ready NLP Deep learning tutorials on tensorflow 2.0. tf-transformers
- Do we really need to Dstill Language Models? Joint loss is all we need - Albert-Joint .
-
tf-transformers : State of the art faster NLP in Tensorflow 2.0 . 80 % faster to existing TF based libraries.
Faster Auto Regressive Decoding using Tensorflow2. Faster than PyTorch in most experiments (V100 GPU). 80% faster compared to existing TF based libraries (relative difference) Refer benchmark code.
- [D] Why is tensorflow so hated on and pytorch is the cool kids framework?
transformers
-
Maxtext: A simple, performant and scalable Jax LLM
Is t5x an encoder/decoder architecture?
Some more general options.
The Flax ecosystem
https://github.com/google/flax?tab=readme-ov-file
or dm-haiku
https://github.com/google-deepmind/dm-haiku
were some of the best developed communities in the Jax AI field
Perhaps the “trax” repo? https://github.com/google/trax
Some HF examples https://github.com/huggingface/transformers/tree/main/exampl...
Sadly it seems much of the work is proprietary these days, but one example could be Grok-1, if you customize the details. https://github.com/xai-org/grok-1/blob/main/run.py
-
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722
I don't think it would be that hard to switch it out for a pretrained ngram model.
-
AI enthusiasm #6 - Finetune any LLM you want💡
Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️
-
Schedule-Free Learning – A New Way to Train
* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013
-
Gemma doesn't suck anymore – 8 bug fixes
Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)
The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285
My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402
- HuggingFace Transformers: Qwen2
- HuggingFace Transformers Release v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2
- HuggingFace: Support for the Mixtral Moe
-
Paris-Based Startup and OpenAI Competitor Mistral AI Valued at $2B
If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...
If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.
-
Fail to reproduce the same evaluation metrics score during inference.
I am aware that using mixed precision reduces the stability of weight and there will be little consistency but don't expect it to be this much. I have attached the graph of evaluation metrics. If someone can give me some insight into this issue, that would be great.
What are some alternatives?
medspacy - Library for clinical NLP with spaCy.
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
flax - Flax is a neural network library for JAX that is designed for flexibility.
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
MIRNet-TFJS - TensorFlow JS models for MIRNet for low-light💡 image enhancement
llama - Inference code for Llama models
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
BERT-for-Mobile - Compares the DistilBERT and MobileBERT architectures for mobile deployments.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
gpt-3-simple-tutorial - Generate SQL from Natural Language Sentences using OpenAI's GPT-3 Model
huggingface_hub - The official Python client for the Huggingface Hub.