datablations
transformers
datablations | transformers | |
---|---|---|
6 | 176 | |
290 | 125,369 | |
3.8% | 1.7% | |
6.9 | 10.0 | |
about 1 month ago | 2 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.
datablations
-
Gemini is only 1x Chinchilla, so it undertrained for production
1x chinchilla means it's not really undertrained but that more could be squeezed without excessive difficulty https://arxiv.org/abs/2305.16264
- Can LLMs learn from a single example?
-
Chinchilla’s Death
You might want to give a read to "Scaling Data-Constrained Language Models" [1]. They basically generalized the Chinchilla scaling law by investigating behavior on multi-epoch runs.
[1] https://arxiv.org/abs/2305.16264
-
RWKV Pile+ seems to be training on far more tokens than any LLM ever has
I would imagine that there is a lot of overlap, yeah. That said, training on repeated data does seem to be effective at this level.
-
(2/2) May 2023
Scaling Data-Constrained Language Models (https://arxiv.org/abs/2305.16264)
- How to Keep Scaling Large Language Models when Data Runs Out? A New AI Research Trains 400 Models with up to 9B Parameters and 900B Tokens to Create an Extension of Chinchilla Scaling Laws for Repeated Data
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?
TinyLlama - The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
airoboros - Customizable implementation of the self-instruct paper.
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
tree-of-thoughts - Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
llama - Inference code for Llama models
prompt-engineering - Tips and tricks for working with Large Language Models like OpenAI's GPT-4.
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
SuperAGI - <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
chathub - All-in-one chatbot client
huggingface_hub - The official Python client for the Huggingface Hub.