Skip to content

Releases: transformerlab/transformerlab-app

0.7.2

28 Dec 01:25
Compare
Choose a tag to compare
v0.7.2

Bump version to 0.7.2

0.7.1

02 Dec 15:41
Compare
Choose a tag to compare
v0.7.1

Bump version to 0.7.1

0.6.2

15 Nov 18:47
Compare
Choose a tag to compare
  • Recipes: alpha release of recipes allows you to import/export training templates via yaml file
  • Improved training data visibility: added fields to preview datasets and samples of rendered templated output
  • Support repeat for batch completions

0.6.1

18 Oct 20:08
Compare
Choose a tag to compare
v0.6.1

Bump version to 0.6.1

0.6.0

10 Oct 13:37
Compare
Choose a tag to compare
  • Simpler installer: Performance improvements and app no longer pauses for user input between steps
  • Tool Use: Early preview of Tool Use / Function Calling in chat with demo weather and calculator tools
  • Batch Prompting: support for executing batches of prompts simultaneously
  • Tokenization Visualizer: Tokenize screen to analyze how a model will tokenize a string
  • Interact Dropdown: Consolidated interaction screens in one screen (incl. "Query Docs", "Embeddings" and many new screens)
  • Better Streaming: Fixes for streaming on "Completions" and "Prompt Templates" pages
  • Export to Hugging Face

0.5.0

19 Aug 15:40
Compare
Choose a tag to compare
v0.5.0

Bump version to 0.5.0

0.4.0

23 Jul 17:14
Compare
Choose a tag to compare

What's New

  • Addition of several new training plugins that support a variety of methods including RLHF, DPO, ORPO, SIMPO and SFT.
  • Initial support for multimodal models
  • Improvements to training interface, including ability to stop a training job
  • Plugins now have readme pages that are displayed in the app

0.3.9

24 Jun 15:51
Compare
Choose a tag to compare
  • Added Qwen 2 models to the gallery
  • Added a number of popular datasets to the gallery
  • Update training templates to use Jinja => requires update to existing training templates
  • You can now edit training templates
  • First UI updates to reorganize training template creation
  • Added a Gated badge to gated models and an explanation and link to any agreements required to use gated models
  • Generated models have a separate page in the model zoo
  • Bug fixes: issues starting up Mistral v0.3 models, downloading models can cause a database lock

0.3.8

04 Jun 14:08
Compare
Choose a tag to compare
  • Installer improvements to fix recently reported permission issues
  • Initial support for importing models including importing from a local directory (only works if you are running LocalConnection API)
  • Adding wikipedia to the data gallery and API support for dataset configurations
  • Added a tag to identify gated models in the Model Zoo
  • PyTorch and flash_attn version added to server info
  • Initial cleanup of API for jobs and plugins

0.3.7

28 May 12:44
Compare
Choose a tag to compare

What's Changed

  • Add Mistral v0.3 and Aya 23 :)
  • You can now preview all of a dataset! @safiyamak added pagination
  • Models that are downloading will show their download status even if you leave and come back to the page!
  • If you go to the Computer Tab you can see all python dependencies and their versions, along with more information on the current conda environment
  • Adding Data Store search feature by @safiyamak in #89
  • Datasets that are downloaded are market appropriately by @safiyamak in #94
  • We added a change that should (hopefully) build official Linux builds
  • Remove the App Menu UI in Linux and Windows
  • Tony continues to add lots of changes to Importing Models -- we will announce this once the entire set of features is complete and tested
  • After upgrading plugins, you should have MLX upgraded to 0.14

New Contributors

Full Changelog: v0.3.6...v0.3.7

API Changelog: transformerlab/transformerlab-api@v0.2.22...v0.2.23