Open Models Almanac
Methodssoftware implementationkernel & quantization library

specific method · filed under software implementation

AngelSlim

AngelSlim is a toolkit for compressing large models.1 It bundles compression tools including common quantization algorithms, low-bit quantization, and speculative sampling, aimed at large-scale multimodal models.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. a more accessible, comprehensive, and efficient toolkit for large model compression — tencent/Hy4-preview · Hugging Face
  2. supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling — tencent/Hy4-preview · Hugging Face

Also called AngelSlim compression toolkit, AngelSlim toolkit.

sources
2
models
2
lab adopt it
1
strongest
used

Documented in

Tencent (Hunyuan)

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
mentioned 1used 1

Hy4-preview

Tencent (Hunyuan)adopted1 source

We provide AngelSlim, a more accessible, comprehensive, and efficient toolkit for large model compression. AngelSlim supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling.

usedpost trainingin Hy4-previewTencent Hy Team
↑