Download Latest Version v0.6.2 source code.tar.gz (5.8 MB)
Email in envelope

Get an email when there's a new version of Bumblebee

Home / v0.6.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2024-10-07 2.1 kB
0
v0.6.0 source code.tar.gz 2024-10-07 5.8 MB
0
v0.6.0 source code.zip 2024-10-07 6.0 MB
0
Totals: 3 Items   11.8 MB 0

Added

  • Notebook about Retrieval-Augmented Generation (RAG) (#353)
  • Phi model (#356)
  • Gemma model (#358)
  • Support for input streaming in Whisper serving (#361)
  • Stable Diffusion ControlNet model (#359)
  • Support for multiple EOS tokens in text generation (#368)
  • Phi-3 model (#374)
  • Support for Llama 3 (#387)
  • Support for CLS token pooling in text embedding (#385)
  • Support for HTTP proxies (#391)
  • M2M100 and NLLB models (#392)
  • Multilingual translation serving (Bumblebee.Text.translation/4) (#395)
  • Swin model (#394)

Changed

  • (Breaking) Renamed :use_qkv_bias spec option to :use_attention_bias in ViT, DeiT and DINOv2
  • (Breaking) Changed spec options for optional outputs (:output_hidden_states, :output_attentions) to global layer options (#360)
  • Whisper serving to stream input using ffmpeg when given a file path (#361)
  • (Breaking) Changed model params to use %Axon.ModelState{}, matching Axon v0.7.0 (#375)

Fixed

  • Token classification crashing when all tokens are special
  • Batched text generation finishing too early
  • Crash on empty list of entities when aggregating entities in token classification (#386)
Source: README.md, updated 2024-10-07