March 7, 2025
v0.3.107

v0.3.107

Autonomous Fine-tuning

  • Added the ability to download fine-tuned models weights.
  • Added the ability to download model weights from an AWS s3 url.
  • Improvements to ML service.
February 26, 2025
v0.3.102

v0.3.102

UI Improvements

  • Upgraded the UI for the autonomous fine-tuning agent.
  • You can now set a default job name.
  • New tooltips in the autonomous fine-tuning agent.
  • New button to copy the format of the json and jsonl.
  • You can now copy paste to insert a dataset.

Autonomous Fine-tuning

  • Added the ability to delete a fine-tuning job.
  • You can now download the default dataset.
  • Update default datasets
February 25, 2025
v0.3.101

v0.3.101

  • Added support for gemma 2, qwen2.5 and codellama models for fine-tuning and inference.
  • Improved fine-tuning evaluation.
  • Improvements to autonomous fine-tuning.
  • Added system prompt for fine-tuned models.
  • Improvements to fine-tuning start and completion emails.
  • Improvements to login page responsiveness.
February 4, 2025
v0.3.100

v0.3.100

  • Improvements to data augmentation.
  • The Gym is now Autonomous Fine-tuning.
February 3, 2025
v0.3.99

v0.3.98

  • Improved logging for creation of user/orginization.
January 31, 2025
v0.3.97

v0.3.97

  • Added support to upload and fetch files from s3.
January 30, 2025
v0.3.96

v0.3.96

  • Improvements to data augmentation.
January 29, 2025
v0.3.94

v0.3.94

  • Improvements to integrations messaging.
  • Added support for Deepseek-r1-distill-70b model.
  • Added support for Deepseek-r1 model.
January 21, 2025
v0.3.93

v0.3.93

  • Bug fixes
  • Deprated llama 3.1 70b model.
January 20, 2025
v0.3.92

v0.3.92

  • Improved chat latency.
January 15, 2025
v0.3.90

v0.3.90

Finetuning

  • Removed finetuning for Groq models.
  • Added fine-tuning evaluation.
  • Improved fine-tuning evaulation metrics.
  • Improved fine-tuning Model deployment.
  • Improved Docker Composed for fine-tuning.

Integrations

  • UI updates for the integrations page.
  • Fixed multiple integration connections.
  • Improved integration deletion UX.
  • Added Notion integration.
  • Added Gmail integration.
  • Added Github integration.
  • You can now activate integrations through the Launchpad.

RAG

  • Added the new bring your own Quadrant Vector Database feature.
December 19, 2024
v0.3.89

v0.3.89

  • Internal model evaluation.
  • Added superuser topbar.
  • Show images in Traces.
  • Deprecated Groq “tool-use” models.
December 19, 2024
v0.3.87

v0.3.87

Added support for the following new models:

  • llama 3.3 70b - Powered by Groq
  • claude-3.5-sonnet-v2
  • claude-3.5-haiku

We’ve also added some new UI updates:

  • New Navigation bar and sidebar. Now it’s easier to navigate the platform.
  • Updated user login view
  • Update privacy policy and terms links

Other additions:

  • When a model is deleted, an email is sent to the user.
November 26, 2024
v0.3.83

v0.3.83

  • Bug fixes: Traces paginator
November 26, 2024
v0.3.82

v0.3.82

  • Removed old trace columns
  • CI improvements
November 26, 2024
v0.3.80

v0.3.80

  • Refactored checkpointing into a scheduler
  • Removed embedding model from repo update form
  • Improved frontend tooling
  • Support for Llama 70B full and lora finetuning
October 22, 2024
v0.3.72

v0.3.72

Improvements

  • Dark Mode Only: We’ve removed the light mode option, focusing on a more streamlined and cohesive dark mode experience.
  • Datasource Improvements: We’ve applied various enhancements and fixes to datasource functionality, improving overall data integration and processing.

Features

  • Document Deletion: You can now delete incomplete documents, allowing for more flexible content management.
  • Pending Invites Management: We’ve introduced a new feature to handle pending invites, allowing users to manage their invitations effectively, including the ability to cancel pending invitations.