β44Jun 19, 2024Updated last year
Alternatives and similar repositories for Zyda_processing
Users that are interested in Zyda_processing are comparing it to the libraries listed below
Sorting:
- See https://github.com/cuda-mode/triton-index/ instead!β11May 8, 2024Updated last year
- π A series of lightweight GPT models featuring TinyGPT Base (~51M params) and TinyGPT-MoE (~85M params), TinyGPT2 (~95M params). Fast, cβ¦β15Feb 21, 2026Updated last week
- A repo to do interpretability of pre-trained acoustic modelsβ15Oct 15, 2023Updated 2 years ago
- Scalable Computation of Hessian Diagonalsβ14Jun 2, 2024Updated last year
- [WIP] Transformer to embed Danbooru labelsetsβ13Mar 31, 2024Updated last year
- gzip Predicts Data-dependent Scaling Lawsβ34May 28, 2024Updated last year
- β18Mar 18, 2024Updated last year
- UTAUTAI(Unrestricted Tune Automated Technology Artificial Interigence)β15Oct 27, 2023Updated 2 years ago
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scaleβ266Jul 8, 2025Updated 7 months ago
- Language models scale reliably with over-training and on downstream tasksβ100Apr 2, 2024Updated last year
- A Chrome extension that helps you stay focused by blocking sites during work timers and letting you browse during break timers. Now also β¦β16Nov 22, 2018Updated 7 years ago
- β18Aug 24, 2024Updated last year
- β20Jul 5, 2024Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"β91Oct 30, 2024Updated last year
- The pipeline for the OSCAR corpusβ176Nov 9, 2025Updated 3 months ago
- 60k hours of phoneme-aligned audio from audio booksβ19Jul 27, 2024Updated last year
- URL downloader supporting checkpointing and continuous checksumming.β19Nov 29, 2023Updated 2 years ago
- TorrentPier. Alternative compiled announcer (Ocelot)β23Jul 12, 2024Updated last year
- β20Nov 4, 2025Updated 3 months ago
- An implementation of the Llama architecture, to instruct and delightβ21May 31, 2025Updated 9 months ago
- β15Apr 26, 2022Updated 3 years ago
- Code for the paper "Function-Space Learning Rates"β25Jun 3, 2025Updated 8 months ago
- A JAX nn libraryβ21Sep 9, 2025Updated 5 months ago
- Source code of our paper "Focus on the Targetβs Vocabulary: Masked Label Smoothing for Machine Translation" @ACL-2022β18May 19, 2022Updated 3 years ago
- The official evaluation suite and dynamic data release for MixEval.β255Nov 10, 2024Updated last year
- Turn jitted jax functions back into python source codeβ23Dec 16, 2024Updated last year
- GPT2 Byte Pair Encoding implementation in Golangβ24Jul 9, 2025Updated 7 months ago
- Utilities for PyTorch distributedβ25Feb 27, 2025Updated last year
- A port of muP to JAX/Haikuβ25Oct 23, 2022Updated 3 years ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Trainingβ23Aug 18, 2024Updated last year
- β20Oct 11, 2022Updated 3 years ago
- β23Jun 18, 2024Updated last year
- QLoRA for Masked Language Modelingβ23Sep 11, 2023Updated 2 years ago
- Multipack distributed sampler for fast padding-free training of LLMsβ204Aug 10, 2024Updated last year
- Griffin MQA + Hawk Linear RNN Hybridβ89Apr 26, 2024Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Trainingβ51Jan 20, 2024Updated 2 years ago
- Benchmarking Optimizers for LLM Pretrainingβ52Dec 30, 2025Updated 2 months ago
- Implementation of Diffusion Transformers and Rectified Flow in Jaxβ27Jul 9, 2024Updated last year
- β21Mar 3, 2025Updated 11 months ago