bk99.de entertain the web since 1997

bk99.de
HF · Open modelsCurated

The open ecosystem for text generation

Summary

The overview classifies open language models, training libraries, inference servers and evaluation tools around the Hub. It makes clear that open LLMs need a chain of compatible components. Models and their associated artefacts are versioned via the Hub.

Ideas

  • A usable model ecosystem covers data, training, evaluation, deployment and documentation.
  • Open interfaces reduce dependence on individual model providers.

Insights

  • Open weights shift control to users and in return require more testing competence of their own.

Critique

  • An overview by a provider can underweight competing tools and unresolved governance questions.

Recommendations

  • Choose components by open formats and interchangeable interfaces, not just by benchmarks.

References

Read the original article on Hugging Face

Search the Web Archive

HF · 2023

Mixtral and mixture of experts

Mixtral activates only part of its experts per token and combines high model capacity with limited computation. The article explains the architecture, usage and open availability. Mixtral uses eight experts and activates two of them per token.

HF · 2022

BLOOM: an open multilingual large model

BLOOM was created as an international community project for open access to a very large language model. The article describes the languages, computing effort and the joint organisation behind the training. BLOOM has 176 billion parameters.

HF · 2020

How decoding changes the text output

The article compares greedy search, beam search, sampling, top-k and nucleus sampling. It shows that the same model weights produce completely different texts depending on the decoding strategy. Beam search keeps several continuations in parallel and compares their overall probability.