ludwig
transformers
ludwig | transformers | |
---|---|---|
3 | 176 | |
10,801 | 125,021 | |
0.8% | 1.4% | |
9.5 | 10.0 | |
9 days ago | 6 days ago | |
Python | 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.
ludwig
-
Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing
This is a great project, little bit similar to https://github.com/ludwig-ai/ludwig, but it includes testing capabilities and ablation.
questions regarding the LLM testing aspect: How extensive is the test coverage for LLM use cases, and what is the current state of this project area? Do you offer any guarantees, or is it considered an open-ended problem?
Would love to see more progress toward this area!
-
Python projects with best practices on Github?
Two random examples I found from 30 seconds of googling: Here’s Netflix using it in their crisis management tool, and here’s Uber using it in their deep learning framework.
-
Most Frequent 600 Coding Questions on LeetCode
They list themselves all over the internet as an "open source contributor" to Uber, which as far I can tell is based entirely on... reporting that there was an issue with a favicon. To me, it seems like they'll be cheating anybody who employs them based on this, ahem, "experience". And that feels like the tip of the iceberg.
transformers
-
AI enthusiasm #9 - A multilingual chatbot📣🈸
transformers is a package by Hugging Face, that helps you interact with models on HF Hub (GitHub)
-
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.
What are some alternatives?
nlp-recipes - Natural Language Processing Best Practices & Examples
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
data-structures-and-algorithms - Resources that I used to crack some big tech & startups interviews
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
aimet - AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
llama - Inference code for Llama models
Robo-Semantic-Segmentation - Just a simple semantic segmentation library that I developed to speed up the image segmentation pipeline
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
ai-deadlines - :alarm_clock: AI conference deadline countdowns
huggingface_hub - The official Python client for the Huggingface Hub.