Alternatives to Kiln
A free desktop workbench for building, evaluating and fine-tuning AI systems, with an open-source library. The listings below can replace it for an important use case. Each note says what changes if you switch.
The original
Kiln
A free desktop workbench for building, evaluating and fine-tuning AI systems, with an open-source library.
Replacements
Listings that take over the same core job as Kiln.
LlamaFactory
Web UI and command-line toolkit for fine-tuning over 100 open language and vision-language models.
LlamaFactory is an Apache-2.0 web UI and CLI focused on fine-tuning over 100 open models, without Kiln's built-in evals and synthetic data tools.
Unsloth
A local interface and command-line tool for running and fine-tuning language and diffusion models.
Unsloth provides a local UI and CLI for running and fine-tuning language and diffusion models, but lacks Kiln's eval and synthetic data features and states no license.
Axolotl
A command-line tool for fine-tuning language models from YAML configuration files.
Axolotl is an Apache-2.0 command-line tool that fine-tunes models from YAML files on Linux, with no graphical app and aimed at people with ML experience.
Also worth comparing
These listings name Kiln as their own alternative, so the relationship runs both ways.
lm-evaluation-harness
EleutherAI's command-line framework for few-shot evaluation of language models on many benchmark tasks.
Kiln moves evaluation into a free desktop app with fine-tuning and synthetic data, replacing the command line with a graphical interface, though the app's license is not stated.
Similar software
Related functionality, not a direct replacement.
DeepEval
An open-source Python framework for unit-testing and evaluating the outputs of large language model applications.
Promptfoo
A command-line tool for testing prompts, evaluating model output and red-teaming LLM applications and agents.
Label Studio
An open-source data labeling tool for building training datasets and reviewing AI output.
MergeKit
A command-line toolkit for merging the weights of pretrained large language models.
