microsoft/torchscale

Foundation Architecture for (M)LLMs

Pythonmachine-learningnatural-language-processingtranslationcomputer-visiontransformerspeech-processingmultimodalpretrained-language-model
This is stars and forks stats for /microsoft/torchscale repository. As of 18 Apr, 2024 this repository has 2576 stars and 169 forks.

TorchScale - A Library of Foundation Architectures TorchScale is a PyTorch library that allows researchers and developers to scale up Transformers efficiently and effectively. Fundamental research to develop new architectures for foundation models and A(G)I, focusing on modeling generality and capability, as well as training stability and efficiency. Stability - DeepNet: scaling Transformers to 1,000 Layers and beyond Generality - Foundation Transformers (Magneto): towards true general-purpose...
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
Extraltodeus/multi-subject-renderPython3410260
channy/korea-devculturePython3060220
mlr-org/mlr3mboRCOther23010
amrvac/amrvacFortranAssemblyPython610350
apache/incubator-celebornJavaScalaShell55802490
QuantumBFS/Yao.jlJuliaJust8300132+4
hwchase17/langchainPythonMakefileXSLT64.2k09.1k0
zhaoolee/insPythonShell2.1k0970
Normation/rudder-techniquesSmalltalkStringTemplateRuby160210
ekzhang/dispictSvelteTypeScriptPython59000