KeelCore

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

saravanan-arjuna-ravi  published a Space about 14 hours ago
KeelCore/README
saravanan-arjuna-ravi  updated a Space about 14 hours ago
KeelCore/README
View all activity

Organization Card

KeelCore: one compact base, small adapters, built to run on your device

KeelCore is one compact base model plus many small LoRA adapters. We pretrain the base once. A new capability then arrives as a small adapter, not a new model, so you download the base once and add only the adapters you need.

KeelCore-750M  ·  Technical report  ·  GitHub  ·  Contact

Models

Model Status Details
KeelCore‑750M Base model 752M parameters, encoder–decoder, 2,048-token context. English, code and command line.

Benchmarks, including where we trail models trained on larger budgets, are on the model card.

Adapters

An adapter is a small, separate download that works only with the base it was trained on. You install the base once, then pick the adapters you need.

Adapter Status
Text-rewriting adapters In training
Other domains, for example legal and marketing writing Planned (no dates)

We plan one repository per adapter, named after the base and the task (KeelCore-750M-<task>), possibly at more than one LoRA rank. This page will list each one when it is released.

Why this approach

  • One base. A single pretrained encoder–decoder with a tokenizer built for English prose, source code and command-line text.
  • Small adapters. A rank-16 LoRA adapter trains about 18.3M parameters, 2.4% of the base, while the base weights stay frozen.
  • Runs on your device. A weight-only int8 ONNX export (0.76 GB) runs in a web browser through ONNX Runtime Web. Because that runtime could not load LoRA adapters, we contributed the support ourselves: a LoraAdapter API and an activeLoraAdapters run option, merged in October 2026 (microsoft/onnxruntime#32886).

Built with KeelCore

EchoMeBetter is the first product built on KeelCore: a browser extension that runs the base and its text-rewriting adapters on your device. It is one application, not the purpose of KeelCore, which is a general base for adapters.

License

Models are released under the KeelCore License, Version 1.0: personal use through the official EchoMeBetter extension and noncommercial research, which requires citing the project. Commercial use, use by an organization and any use outside the extension need a separate written agreement. Adapters follow the same terms unless their repository says otherwise.

Contact

Saravanan A R · LinkedIn · GitHub

Commercial licensing and partnerships: sararavi.ar@gmail.com

models 0

None public yet

datasets 0

None public yet