Transformer Lab: baixar versions anteriors

Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.7...v0.27.8

Hotfix to prevent alembic migration from failing if you are updating from certain old versions.
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.6...v0.27.7

Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.5...v0.27.6

What's Changed
- Fixed experiment creation before experiments are loaded bug by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/1109
- Changed path where controller.log is saved by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/1110
- Add VSCode interactive support by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1074
- Add parameterization and sweeps by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1081
- Pin numba and remove --upgrade flag from uv pip install by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1113
- One liner: Add check for providers array before using .map() by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/1108
- Remove librosa from main pyproject.toml and add it to plugin specific setup files by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1114
- Add GCS as option for fsspec by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/1091
- Change date on deprecation announcement by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1115
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.4...v0.27.5

HIghlights
- Added Z Image model support
- Bug fix: Change logic for upload dataset in plugin sdk
What's Changed
- Add/compute resources by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/1056
- Fix VSCode launch configuration for TransformerLab by @josh-janes in https://github.com/transformerlab/transformerlab-app/pull/1077
- Make tasks gallery imports also use task.json if available by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1078
- Remove a separate step to fetch task.json by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1068
- Add usage report by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1036
- Make all job get json calls uncached by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1082
- Restore sidebar update by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/1080
- Append jwt secrets to env file if file exists without secrets by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1093
- Add/compute resource slurm by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/1084
- Added Z Image model support by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/1079
- Dont run over and over in s3 mode by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1101
- Change logic for upload dataset in plugin sdk to avoid auth or requests altogether by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1100
- Remove titleBarStyle to prevent sidebar overlap on macos by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1103
- Show some default configs when adding a new provider by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1096
- First CLI by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/1097
- Fix users router to work with api key auth by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1095
- Allow viewing and downloading image, video, json, txt and other popular artifacts by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1102
- Add/remove compute cluster by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/1104
- Fix for UI Bug with Github PATs by @josh-janes in https://github.com/transformerlab/transformerlab-app/pull/1106
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.3...v0.27.4

What's Changed
- Temporarily revert sidebar spacing by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/1076
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.2...v0.27.3

What's Changed
- make auto login polling when doing local connection by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/1061
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.27.0...v0.27.1

Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.26.3...v0.26.4

What's Changed
- Fix direct connection to login modal by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/909
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.26.2...v0.26.3

What's Changed
- Add logo for tasks gallery and fix the tasks list visuals by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/863
- Added a Stopping message after clicking the stop button by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/865
- Changed /job routes in train.py to /experiments/jobs on frontend by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/851
- Fixes import on diffusion history page to allow history card to open by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/869
- Fix blank outputs in tasks terminal by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/866
- Add refresh button for models list on local models by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/867
- Fix for broken doc link by @josh-janes in https://github.com/transformerlab/transformerlab-app/pull/872
- Show a skeleton while searching for the appropriate inference engine instead of the temporary error by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/871
- Change Tasks Job List to display Instance Name and User Info if available by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/839
- Fix wrong path in useAPI for outputmodal by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/870
- Fixed a broken link in Getting Started section by @defkorean in https://github.com/transformerlab/transformerlab-app/pull/873
- Streaming Request Logs Fixes by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/846
- Fix login loader to keep showing logging in until auth/me is successful by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/864
- Fix broken docs links by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/874
- Add/resume training checkpoint by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/828
- Add subtypes to jobs to show up filtered in Train, Eval and Generate Tabs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/860
- Enable auto-teardown of instances by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/831
- Queue jobs to existing clusters by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/847
- Fixed Delay in cursor activation and typing in ModelGroups page by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/843
- Change model progress to track number of files downloaded by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/877
- Fixed system prompt reset functionality in All generation settings and interact page by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/838
- Add/audio stt by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/719
New Contributors
- @josh-janes made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/872
- @defkorean made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/873
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.24.2...v0.25.0

What's Changed
- Made error more clearer when curl is not installed by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/849
- Fixed Logs page issue by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/844
- Fixed Foundation page glitch on model load by @ParamThakkar123 in https://github.com/transformerlab/transformerlab-app/pull/857
- Fix editing of all kinds of tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/862
New Contributors
- @ParamThakkar123 made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/849
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.24.1...v0.24.2

What's Changed
- Fixes conditions when a value is set to 0 and blank is sent instead due to truthy condition failure by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/856
- Add jobs placeholder skeleton until the new job id is included in the jobs list results by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/842
- fix issue of edit task modal losing parameters, also fix the polling logs going on after 404 by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/845
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.24.0...v0.24.1

What's Changed
- Fix diffusion calls to also include experiment id by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/788
- Add batched generation button and modal for audio by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/792
- Login with WorkOS in cloud mode by @mashcroft3 in https://github.com/transformerlab/transformerlab-app/pull/790
- Fix local dataset card buttons by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/794
- Fix some routes that dont have credentials included by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/797
- Fix/experiment id name by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/795
- Remove workflows from sidebar by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/801
- add tasks in side panel and hide others by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/802
- add authfetch for recipe calls by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/805
- Remote launch tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/806
- Add check for prettier (linter) to enable latest changes update before merging by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/804
- Add a separate polling terminal for auth outputs in tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/807
- Fix healthz check app init by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/809
- Create tasks and launch separately , also adds upload directory and edit tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/811
- add monaco editor to create task by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/816
- Added option to update Hugging Face credentials in UI by @salsina in https://github.com/transformerlab/transformerlab-app/pull/798
- Add WANDB Run URL button for jobs in tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/817
- Hide settings from Sidebar in GPU Orchestration mode by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/818
- Add tasks library by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/814
- Don't show current model running if in GPU Orchestration mode by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/812
- Switch to GPU Orchestration from TLAB by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/819
- View Artifacts and Checkpoints in the Tasks jobs list by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/815
- Add loading menu item when experiments are loading by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/824
- wrap task run buttons better by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/823
- Fix saving of notes when logged in by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/825
- Load Task List and Jobs List separately by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/826
- Allow Remote Jobs to be Stopped and Allow completion without lab facade by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/827
- Separate out job create and launch for remote jobs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/829
- Add change task library behaviour by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/830
- Fix state reset in Task Library file viewer by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/833
New Contributors
- @mashcroft3 made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/790
- @salsina made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/798
Full Changelog: https://githu

What's Changed
- Fix undefined error id screen upon losing connection to API by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/772
- Fix Output Terminal going blank when re-connecting to another API server by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/775
- Model groups search bar now looks at more things than just model groups name by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/770
- Add no model is running pop-up upon model disconnection to audio screen by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/778
- This fix removes the duplication of native + wavesurfer audio players… by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/776
- Add Top P field for audio by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/777
- Fix/audio cloning upload by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/781
- Dont show nan in text if another model is deleted while downloading by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/784
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.23.0...v0.23.1

What's Changed
- Fix native element in audio player by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/748
- Fix no training plugins message and some typos by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/757
- Add/audio cloning by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/746
- Add/adaptor name audio by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/761
- Add text-to-audio as an Audio pipelineTag by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/765
- Add adaptor name in audioplayer by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/762
- Fix/disable audio cloning mlx by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/766
- Add/voice audio by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/749
- Fix Tool Calling by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/736
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.22.0...v0.23.0

Highlights:
- Alpha release of Text-to-Speech support including generation on CUDA and MLX, and training on CUDA!
- Ability to trigger a workflow through transformerlab-client
- Fix for the stalling download error some users were getting on gated models
- Diffusion has been converted to run as a plugin like other loaders
- Upgrades to key libraries to support newest models (torch, transformers)
- API reorganization to move jobs under experiments
What's Changed
- Remove audio URL from UI after speech is generated by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/720
- Move Jobs Router under Experiment by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/701
- Fix Audio Player for datasets preview by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/729
- Fix stopping of jobs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/739
- Update Old Job Endpoints under Experiment by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/740
- Fix/audio engine filtering by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/733
- Convert Image Diffusion to a Plugin by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/628
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.21.1...v0.22.0

What's Changed
- Add checkpointing UI by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/711
- Add support for downloading audio datasets from HF by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/709
- Add custom url for tensorboard modal by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/685
- Add/audio tts by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/710
- Change audio output path by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/715
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.7...v0.21.1

What's Changed
- Improve README.md to show that we support stable diffusion in addition to LLMs
- Fix Plugin Architecture decision in Export Modal
- Improve rendering of job progress
- Add IDE files to gitignore
New Contributors:
@michael-haroon
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.6...v0.20.7

Potential fix for Windows AutoUpdate
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.4...v0.20.5

What's Changed
- fix form validation ux for LoRA modal by @MashDevel in https://github.com/transformerlab/transformerlab-app/pull/673
- Hide incompatible plugins in dropdown by @MashDevel in https://github.com/transformerlab/transformerlab-app/pull/682
- Fix system message by adding a override button by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/670
- Fix CSS for long experiment names by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/688
- Dont install a plugin if no experiment is selected by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/686
- Make plugin install non experiment dependent by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/691
- Show Error When Chat Column Is Not in Valid Message Format by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/695
New Contributors
- @MashDevel made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/673
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.3...v0.20.4

What's Changed
- Don't show CPU recipes on CUDA or MLX by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/679
- version 2 of the list recipes screen by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/677
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.2...v0.20.3

This is a patch release with some helpful features and bug fixes including:
- training with chat templates: automatically apply chat templates when training on datasets of conversations
- VLM training: use combined image and text datasets on LoRA finetunes
- A number of UI improvements to Training, Generate and Evaluation modals
- fix for docker image so llama.cpp plugin works properly
- plus many more stability and UI fixes
Detailed Log
- Make export page look exactly like evals and generate by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/649
- Fix Close button on Workflow Runs Output Modal by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/636
- Fixed Workflow runs Training Jobs Streaming by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/634
- Add chat column into config by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/643
- Fix ModelProviderWidget to have an option to also specify loader plugin by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/652
- Fix editing task names in Train and Evaluate by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/647
- Include evaluation steps in GEval Widget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/658
- Add Progress Bar to Workflow Runs by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/656
- Make Workflow JSON Editable in UI by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/666
- Use the job streaming route for train outputs too by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/668
- Fix recipe install logic to improve performance for plugins and dataset install by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/665
- Fix selection of tasks with duplicate names and set default mode as TRAIN by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/663
- Fix system message reset by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/638
- Fix blank system message when starting a model by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/669
- Add/activate-recipes-for-everyone by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/601
- Remove Training Recipes from the App by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/660
- Fix Workflow JSON in dark mode by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/671
- Workflows can only add tasks within experiment by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/648
- Show Apply Chat Template toggle only for specific plugin types by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/657
- Fix Editing, Saving on TRAIN, EVAL and GENERATE by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/674
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.1...v0.20.2

What's Changed
- Move experimentInfo into a useContext thing by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/630
- Make exporter jobs execute as tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/637
- Add login flow by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/530
- Fix going to step 2 for recipes by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/641
- Send adaptor names when running a model with adaptor by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/644
- Change GetFullPath to getAPIFullPath throughout the codebase by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/646
- Display sweep config by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/605
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.20.0...v0.20.1

- The biggest addition in this release is addition of Diffusion ControlNets!
Also:
- new non-interrupting app notifications system
- View chat templates for a foundation model
- several UI bufixes for Workflows
What's Changed
- Added runs reload when switching experiments by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/555
- fix segment analytics using context properly by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/563
- Run prettier on entire codebase to avoid linter diffs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/566
- ControlNets plus ability to view processed reference image by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/543
- Allow Generate Tab to be active without a foundation model by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/567
- Cancel Workflow Run by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/560
- Don't allow workflows of the same name by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/569
- Add chat template tokenizer by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/561
- Make the ui better by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/570
- Update first supported engine within experiment config db as well by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/572
- Add an app-wide notifications system and remove alerts from workflows by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/564
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.19.1...v0.19.2

Highlights
- support for schedulers when using diffusion
- support for minP as a generation parameter
- several fixes for docker support, and we now use a single Dockerfile for all platforms
- trains will now use the first unused split in a dataset if there is no "train" split
- upgrades to MLX LoRA trainer to better support Qwen models
- fix for embedding dataset creation using Synthesizer Docs plugin
- run a model on an inference engine even if the architecture is not listed as supported
Details
- schedulers drop-down in Diffusion tab by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/539
- Add Minimum P sampling for all generations by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/538
- Model architecture override by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/519
- Fix issues related to unsupported engine checkbox by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/546
- Add model architecture on server start by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/540
- Moved entire Workflows router under Experiment by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/531
- Fix default inference engine logic for new experiment by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/554
- Fix errors showing up in console from Import Models modal by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/548
- Add Alert Message on Workflow Start by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/553
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.19.0...v0.19.1

This release introduces support for diffusion models including inference, training and improved management of image datasets.
What's Changed
- Make Workflows tab visible by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/517
- V1 of adaptors search and install for models by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/514
- Added creation and preview of local image datasets with in place caption editing and searching abilities by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/498
- fix for drag and drop for image datasets by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/523
- Workflows belong to Experiments by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/525
- Track job queue events by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/516
- Fix errant API calls on Model Zoo by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/524
- Export experiment to recipe JSON by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/520
- Fix information for GPU metrics on Header in Mac by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/532
- Added the same dataset preview logic that exists in the Dataset tab to the Generate tab by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/533
- Add Diffusion by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/488
- Fix/separate-use-analytics by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/536
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.18.0...v0.19.0

The most exciting new feature is support for multimodal model training. This includes a VLM trainer and the ability to work with vision datasets.
Notable bug fixes:
- Canceling downloads is a lot more responsive
- LlamaIndex plugin setup error causing issues for some RAG users
- removed limit on the number of samples being used for trains on STF Llama Factory plugin
- Eval and Generate jobs no longer show as COMPLETE when they were STOPPED
What's Changed
- v1 of the Recipes Modal (hidden in DEV_MODE) by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/495
- Preview Image Data in Datasets Tab by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/470
- Changed the visuals in Download Progress Bar by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/491
- Mark plugin as deprecated if supported_hardware_architectures is an empty list by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/494
- Add MCP Server support in Tools tab within Interact tab by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/468
- Recipe navigates to Notes page by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/509
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.17.1...v0.18.0

What's Changed
- Fix apple compatibility machine type by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/497
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.17.0...v0.17.1

- AMD GPU Support!
- New Model Zoo groups models to make it easier to navigate
- Export screen updated to match style of other job pages
- Dataset fixes: Better viewing of ChatML datasets, fixed issues using some of our gallery datasets
What's Changed
- Add a tab for running Sweeps by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/382
- Add/model-groups-with-tags-search-bar by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/477
- Fixed the Preview Dataset feature for ChatML style datasets by @Sourenm in https://github.com/transformerlab/transformerlab-app/pull/479
- Fix tab for model zoo sidebar by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/482
- Recipe Modal by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/484
- fix model store option default in foundation section by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/486
- Make the 'New' button dropdown in the Train section scrollable by @mina-parham in https://github.com/transformerlab/transformerlab-app/pull/487
- Make Exporter Page Match Others by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/467
- receipes: fake loading of dependencies by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/490
- Fix Local Models Download bar, inference destructuring and experimental plugin card overflows by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/489
- Use datasets.path instead of datasets.name while creating a task from recipe by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/492
- Add support for the new Claude 4 models by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/493
- Add support for AMD GPUs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/425
- One liner change for correct machine type by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/496
New Contributors
- @mina-parham made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/486
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.16.4...v0.17.0

What's Changed
- Github build upset about outputs in publish.yml by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/475
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.16.3...v0.16.4

What's Changed
- Fix creating a new experiment by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/458
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.16.0...v0.16.1

- Major update to CUDA and torch in order to add support for NVIDIA 50 series GPUS
- new MLX PPO Trainer plugin!
- ability to run 4-bit bitsandbytes models in fastchat
Bug fixes
- local and generated datasets viewing doesn’t throw an error
- ability to manually set fallback context length used by MLX
- names of task templates update correctly
What's Changed
- Fix internal error on Datasets tab due to name field by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/444
- Add/further sdk cleanup by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/447
- Add logic to filter experimental plugins by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/451
- Fix rendering of eval and generate configs on update by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/455
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.15.2...v0.16.0

Highlights
This build fixes an installer bug that was caused by the latest API update.
What's Changed
- Simplify transformerlab api sdk by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/418
- Fixed dropdown dark mode background by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/434
- If Plugin install fails, show a message by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/430
- Remove unneeded API call on startup by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/435
- Split up transformerlab-api-sdk into components by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/438
- Add/first-example-of-using-new-sdk by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/441
- Added input field to CSS by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/437
- All exporter plugins showing 'Exporting...' when one runs by @aahaanmaini in https://github.com/transformerlab/transformerlab-app/pull/442
- Fix info icon for training jobs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/445
- Change key dependency name to transformerlab-inference to fix broken installer by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/446
New Contributors
- @aahaanmaini made their first contribution in https://github.com/transformerlab/transformerlab-app/pull/434
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.15.1...v0.15.2

This is a patch release with a number of bug fixes:
- Web app will auto-connect to API running on the same machine
- Installer no longer halts if local_server.log is not accessible/writable
- Console automatically opens to show error if inference server fails to start correctly
- Console logger scrolls way faster
- Plugins no longer always say they are unsupported for non-GPU/mac users
- if you upload docs before installing RAG plugin it will index the docs for you before running your query
- You can now edit the setup script for plugins inside Transformer Lab (good for debugging or making custom modifications to a plugin’s venv)
git Details
- Open console logger upon a failed inference server run by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/415
- Fix supported arch message for local plugins by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/417
- Fix error caused by deleting plugins by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/419
- If you are on the webapp, correctly find the local server we should first try to connect to by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/421
- Don't hang or crash if local_server.log is not writeable by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/423
- Reduce console scroll delay from 100ms to 10ms by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/428
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.15.0...v0.15.1

Highlights
- Qwen 3 Support!
- Updated Llama.cpp fixes installation issues for some users and now runs most recent models (including Gemma 3 and Qwen 3)
- Mac specific GPU metrics on Computer page supplied by MacMon library
Many bug fixes including:
- fixed inaccurate token count in interact tab
- cloud-hosted apps now automatically look for API server on the origin machine, not localhost
- filter plugins to those supported by server architecture
- option to delete models from Hugging Face cache when removing from Transformer Lab
- times show up correctly in train/eval tabs when server and app are in different timezones
What's Changed
- Show Dataset Name on Data card if available by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/414
- Have the Cloud App look for the API on the current server by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/396
- Add MacMon Specific Metrics by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/400
- Add filtering based on the supports field for interact in loader plugins by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/399
- Fix Token Count in Interact tab by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/397
- Replace workflow Run display with a table by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/401
- Auto update plugins by enabling a setting in the Settings tab by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/391
- Improve the look of workflow nodes by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/402
- Fix start time to not show future times by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/404
- Fix the app restart on crash by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/405
- Add graph for VRAM usage in header for MLX by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/411
- Delete models from HF cache by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/410
Full Changelog (part 1): https://github.com/transformerlab/transformerlab-app/compare/v0.14.1...v0.14.2
Full Changelog (part 2): https://github.com/transformerlab/transformerlab-app/compare/v0.14.2...v0.15.0

The big update in this version if a move from Miniconda to Miniforge! Big thanks to @brunodoamaral for the groundwork on this!
Some other highlights:
- UX improvements: Faster model downloads, cleaned up foundation screen, more compact sidebar
- Bug fixes: GPU detection error fixed by @kolithawarnakulasooriya, robustness improvements following last week’s rollout of using uv venv’s
More details
- basic runs UI by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/394
- tigher look and feel for the sidebar by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/393
- Add tabs within Foundation section by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/390
- Check conda existence in miniforge3 instead of miniconda3 by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/395
Full Changelog pt 1: https://github.com/transformerlab/transformerlab-app/compare/v0.13.9...v0.14.0
Full Changelog pt 2: https://github.com/transformerlab/transformerlab-app/compare/v0.14.0...v0.14.1

What's Changed
- Show error when downloading unauthorized HF model. by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/363
- Simplify command to publish webapp zip file on release. by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/362
- Add useEffect to select the first available workflow by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/367
- Add support for GPT 4.1 models by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/366
- Create a tar.gz file instead of a zip when building the app by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/368
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.13.1...v0.13.2

Highlights
- Visualize model activations on MLX and Fastchat!
- Plugins: update all at once, show which are supported on your architecture
- Enhanced model provenance
- Improvements to pre-training to support making larger models
- Many backend bug fixes
This release also introduces a pretty significant update to how we handle tasks on the backend that will allow us to launch a powerful workflow GUI in the next couple of releases!
Full github log
- Workflow by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/336
- fix add recipe from yaml with tasks by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/339
- Show if a plugin will work on your machine by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/337
- Fix eval screen by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/340
- Filter by experiment ID by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/342
- Fix/improve embeddings page by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/341
- Add model activations in Interact tab by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/343
- Fix generate and eval modal for enabling editing and proper tab display by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/344
- Add MLX server in the under construction sign for Model Activations by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/345
- Fix/remove calls to node process to make cloud app work by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/347
- Add/update-all-plugins-button by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/348
- Fix things broken by Tasks by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/346
- Add prettier as default formatter for javascript stuff by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/349
- Enhance how model provenance looks and make it working for chains by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/350
- Add code to update Run button state on experiment update to avoid UI delay by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/351
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.11.2...v0.12.0

Highlights
- AirLLM for MLX: run models larger than your available GPU memory!
- Fastchat server: Gemma3 support, and Evaluate logprobs now works
- Embeddings: correctly uses selected embedding model, several fixes to training plugin
- Ollama Server is the now the default server plugin for users without a GPU or MLX
Specific additions to Evaluations:
- Custom evals: create your own evals using custom python code
- Red Teaming Plugin: generate detailed reports of potential vulnerabilities in your LLMs
- GEval: Enter a description to DeepEval LLM-as-Judge to create an evaluation metric for you automatically
Full github notes
- Add GEval Widget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/324
- Change Process Embeddings to use in-built embeddings function by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/323
- Change string comparison to exact equals to prevent collision issues by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/325
- Fixes reset to default embedding and adds embedding to experiment json on new setup by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/327
- Remove ipc for darkmode (it wasn't used) by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/326
- Remove under construction message from visualize logprobs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/328
- Add option for Code return type in the widget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/332
- Fix/screen-size-adjustments-for-cloud by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/331
- I don't think preload-cloud was actually doing anything by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/330
- Divide evals menu in dataset-based and model-based by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/334
- Add Azure OpenAI option in settings and enable in ModelProviderWidget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/338
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.11.1...v0.11.2

Updates:
- You can now run Transformer Lab as a web app! (details to follow)
- Upgraded MLX to support several new models including Gemma3.
- Embeddings: Set separate embedding model per experiment and use that model on Embeddings tab
- Plugins: Display supported hardware architecture, new plugin for generating quality RAG QnA pairs
- Basic anonymized analytics that you can opt-out of (details to follow)
- Several bugfixes including issues loading and deleting adapters. and for documents within folders
New Model Support:
- We now support the new LGAI Exaone Deep Models (2.4B, 7.8B and 32B)
- We also support the Mistral Small 3.1 24B Instruct 2503
- Added support includes enabling training Gemma 3 on MLX
More details
- Add 0 values to radar chart inplace of undefined to stop breaking by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/307
- add a tint color to the background of plugins by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/310
- show supported architectures in plugins list by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/311
- add workflows(at least very basic support) by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/312
- Fix clashing with plugin config fields which have the words dataset in it by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/316
- detailed metric comparisons can be done up and down by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/318
- tasks by @sanjaycal in https://github.com/transformerlab/transformerlab-app/pull/319
- Remove duplicate timestamp from below the eval name by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/320
- Add/embedding model info by @abhimazu in https://github.com/transformerlab/transformerlab-app/pull/321
- Add start:cloud target to serve TransformerLab on web by @dadmobile in https://github.com/transformerlab/transformerlab-app/pull/322
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.11.0...v0.11.1

Installer + Settings
- A new Settings UI allows you to configure third-party LLM services like OpenAI and Anthropic. These services can be used throughout the app for tasks like judging or data generation.
- For debugging purposes, you can view all active engine tasks in Settings → Jobs.
- The Computer Tab now includes a scrollbar when you have more than 3 GPUs, so you can see all your GPUs (must be nice!).
- Fixed a bug where having a .python_version file in your home directory would interfere with uv's Python version selection.
- The new AI Providers tab in Settings lets you add API keys for OpenAI, Anthropic, and custom providers:
- API keys now persist between app startups
- Custom Model Provider APIs can be configured here and used for evaluations or generation
Datasets
- We improved how datasets display, particularly those containing very large fields
- Datasets requiring a config_name now allow you to specify the config during download
Documents
- Fixed bugs affecting document deletion and updates for files stored in folders
- Added the ability to sort documents by name
- Improved the visual design of the Documents page
Evals
- Charting
- Visualize individual evals using line, bar, or radar graphs
- Compare multiple evals using interactive charts
- Generate detailed comparative reports between evals
- Enhanced chart visuals with improved legends and formatting
- Comparing Evals
- Compare results across multiple eval runs
- Generate detailed side-by-side comparisons for each test case, with downloadable CSV reports
- View summary charts comparing all selected eval jobs
- Display line graphs with flexible axis options—view by metric or by compared job
- New Eval Plugins:
- Basic Evals Plugin: Perform fundamental checks on model outputs, including JSON validation and bullet list detection
- Create custom evaluations using regex patterns or exact string matching
- Red Teaming Plugin: Test LLM vulnerabilities using DeepEval's capabilities across multiple categories: Bias, Misinformation, PII Leakage, Personal Safety, Toxicity, Robustness, Unauthorized Access, Illegal Activity, Graphic Content, and Intellectual Property Infringement
- Common EleutherAI Harness Plugin: Run key benchmarks using a streamlined version of the EleutherAI Harness plugin
Training:
- Multi-GPU support
- Multi-GPU training support for Llama Trainer via dedicated plugin
- GRPO training support with multi-GPU configuration on a separate plugin
- Pre-training
- New pre-training plugin using Nanotron for LLMs, initially supporting LlamaForCausalLM config with planned expansion to MoE and Mamba (state-space) models
- Embedding Models: Fine-tune embedding models with comprehensive dataset types and loss functions
- Supports all dataset types and loss functions documented at https://sbert.net/docs/sentence_transformer/loss_overview.html
- Models are automatically stored locally and imported into Transformer Lab
- Support for FP16 and BF16 options
- Additional loss modifiers for model size and performance optimization
Backend:
- SQLAlchemy Integration
- Started migrating database access to SQLAlchemy, enabling future ORM capabilities and Alembic migrations
- Testing Infrastructure
- Implemented foundational unit tests using pytest
- Docker:
- Updated CPU and GPU Dockerfiles in main branch
- Published v0.10.2 CPU and GPU images to Transformer Lab dockerhub
- Updated docker-compose file for direct execution
- Verified CPU docker images on Mac, Ubuntu, and Windows
- Fixed local model import issue
- Enhanced API Security
- Strengthened API endpoints to ensure compliance with future security audits

What's Changed
- Fix GenerateModal to handle the select PickADocument form type by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/265
- Allow setting a fixed folder from outside the Documents component. by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/267
- Add Wandb API Key in settings by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/271
- Elevate selectedDocs to parent component to maintain state and... by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/272
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.10.1...v0.10.2

What's Changed
- Bump the npm_and_yarn group with 5 updates by @dependabot in https://github.com/transformerlab/transformerlab-app/pull/256
- Cancel Model Download by @abhimazu in https://github.com/transformerlab/transformerlab-app/pull/263
- Fix bug which caused document preview issues within folders by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/264
-
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.10.0...v0.10.1

Ollama Plugin: If you have ollama installed you can now use that to server GGUF models instead of llama.cpp
Generate tab: Generate your own datasets using documents, raw text or from scratch. (You can use to train!)
Documents tab: Dedicated page to upload and maintain all documents (for RAG or Generate)
Evals: Downloadable detailed reports for eval tasks, ability to search for tasks
Training: New python completion recipe, several recipe optimizations, added learning rate algorithms to llama_trainer
Bug fixes including:
- Removed dependencies on unzip, detect if curl is missing
- Helpful message when you don’t have an available inference engine
- A number of fixes for issues when using LoRA adapters
- logprobs no longer freezes when max tokens is reduced