Releases: Kiln-AI/Kiln
Kiln Desktop - v0.11.1
⬇️ Download links in the "Assets" section below ⬇️
This release focuses on making Kiln easier to use, across lots of small fixes.
New features include:
- Synthetic data generation is 25x faster
- Windows Code Signing which means fewer "Unrecognized app" prompts, and virus false positives
- Resolve a bugs causing a blank screen on some Windows 11 machines
- Improved Ollama support when using structured data (JSON)
- You can disconnect AI providers from settings UI, without editing config files
- Improved docs, and links to the docs from within the app
- Add the ability to clone a task, copying all it's fields
- Show synthetic dataset topic in the datasets view
CI Build Source for this release Mac and Linux: Kiln-AI/Kiln/actions/runs/13234579948 and Windows: Kiln-AI/Kiln/actions/runs/13234579954
Full Changelog: v0.10.1...v0.11.1
Kiln Desktop - v0.10.1
⬇️ Download links in the "Assets" section below ⬇️
Note: v0.10.1 is a minor release with a bug fix that blocked new users from running models. The remainder of the release notes are features new in v0.10 which shipped yesterday.
New features include:
- Add support for reasoning models, including the ability to distill your own reasoning model. Docs
- Many new models: R1, R1 distills, Mistral Small 3, Phi 4, and Gemini 2.0 flash
- Improved structured data generation (JSON)
- Fine-tuning prompt alignment: use the prompt system the model was tuned with by default.
- Support for the new faster Fireworks V2 fine-tuning system
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/13192037218
Full Changelog: v0.10.0...v0.10.1
Kiln Desktop - v0.10.0
⬇️ Download links in the "Assets" section below ⬇️
New features include:
- Add support for reasoning models, including the ability to distill your own reasoning model. Docs
- Many new models: R1, R1 distills, Mistral Small 3, Phi 4
- Improved structured data generation (JSON)
- Fine-tuning prompt alignment: use the prompt system the model was tuned with by default.
- Support for the new faster Fireworks V2 fine-tuning system
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/13148150574
New Contributors
- @SimonCoulombe made their first contribution in #109
- @bvqbao made their first contribution in #117
Full Changelog: v0.9.0-beta...v0.10.0-beta
Kiln Desktop - v0.9.0-beta
⬇️ Download links in the "Assets" section below ⬇️
This release adds many of our top requested features:
- New Docs website
- Custom Prompts: Add your own custom prompts to any task, including syncing with your team, linking runs with their prompts
- New Prompt UI: Nicer "Prompts" tab including generative and custom prompts
- Many performance improvements: the Dataset view is over 100x faster and the app is faster to start
- New UI for using raw JSON schema (in addition to the existing visual schema builder)
- Dataset view enhancements: multi-select
- Fix unicode escaping (from @leonardmq)
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/12724672910
New Contributors
- @leonardmq made their first contribution in #94 and #102
Full Changelog: v0.8.0-beta...v0.9.0-beta
Kiln Desktop - v0.8.0-beta
⬇️ Download links in the "Assets" section below ⬇️
This release adds many of our top requested features:
- Use any OpenAI compatible server
- New "tags" feature allowing you to organize you data into subsets
- Additional rating types: pass/fail, pass/fail/critical
- Performance improvements: >99% faster on large datasets
- Navigate your dataset with keyboard shortcuts
- Improved developer experience and docs for the python library
- New guide for collaboration (sharing datasets with your team)
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/12434305437
Note for Windows Users: The app may show up as "unrecognized" because it's new, but can be launched from the "More Info" link.
Full Changelog: v0.7.0-beta...v0.8.0-beta
Kiln Desktop - v0.7.0-beta -- Fine-tuning
Download links in the "Assets" section below ⬇️
This release adds ✨fine tuning✨! You can create fine tuned models in a few clicks using your Kiln dataset. Models are automatically deployed to serverless environments. We support Llama 3.1, Llama 3.2, GPT 4o/4o-mini, and Mixtral through the UI, and exporting files for fine tuning on any platform. See our fine tune guide for details.
Smaller changes include adding more models (Qwen 2.5, Mixtral), adding Fireworks.ai as a provider, and experimental Linux builds.
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/12214356310
Note for Windows Users: The app may show up as "unrecognized" because it's new, but can be launched from the "More Info" link.
Full Changelog: v0.6.0-beta...v0.7.0-beta
Kiln Desktop - v0.6.0-beta
Download links in the "Assets" section below.
This new Kiln desktop release adds a powerful and easy to synthetic data generation. Create data for your Kiln tasks with topic trees, human guidance and interactive UI. Great for generating fine-tuning data, test data, or resolving issues.
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/11935414303
Note for Windows Users: The app may show up as "unrecognized" because it's new, but can be launched from the "More Info" link.
Kiln Desktop - v0.5.6-beta
This new Kiln desktop release adds new chain of though (COT) prompting, custom COT instructions, new models (Gemini, Nemotron) and lots of polish.
Download it from the links in the "Assets" section below.
CI Build Source for this release: Kiln-AI/Kiln/actions/runs/11809538168
Note for Windows Users: The app may show up as "unrecognized" because it's new, but can be launched from the "More Info" link.
Kiln Desktop - v0.5-beta
Our Kiln AI Desktop app beta release!
Key Features
- 🚀 Intuitive Desktop Apps: Apps for Windows and MacOS. Anyone on your team can contribute to your datasets & feedback to improve quality, without code.
- 🤝 Team Collaboration: Designed for collaboration, with git-based version control for your ML dataset.
- 📊 Rapid Evaluation: Compare various models and data-science techniques with no-code tools.
- 🔄 Iterative Improvement: Continuous dataset improvement with built-in evaluation, RLHF and QA tooling.
- 🧑💻 Hackers Delight: An open-source Python library and REST API for data scientists and engineers to deeply integrate if needed.
- 🔒 Privacy-First: We can't see your data. Bring your own API keys or run locally with Ollama.
- 🗃️ Structured Data: Build AI tasks which speak JSON. Build training datasets with validated formats, human feedback, issue tracking, and more.
- 💰 Free: Our apps are free to use, and our library is open-source.
CI Build Source for this release: https://github.com/Kiln-AI/Kiln/actions/runs/11707325715
v0.1.3 Alpha
An early release for alpha users.