SKaiNET good first issues (Kotlin)

[Lane 2 · kotlin-core] tokenizer.json parity — accept the array form of model.merges 6 days ago

good first issue sub-issue coding skill:kotlin-core size:xs

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 4 · numerics] tokenizer.json parity — golden encode fixtures from Hugging Face tokenizers for the ModernBERT and mmBERT files 6 days ago

good first issue sub-issue coding skill:numerics size:xs

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 5 · docs] tokenizer.json parity — reference page: tokenizer.json support matrix 6 days ago

documentation good first issue sub-issue skill:docs size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 4 · kotlin-core] tokenizer.json parity — fixture-gated jvmTest replaying the goldens through TokenizerFactory.fromTokenizerJson 6 days ago

good first issue sub-issue coding skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 2 · kotlin-core] tokenizer.json parity — match non-special added_tokens atomically and count them in vocabSize 6 days ago

good first issue sub-issue coding skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 1 · numerics] tokenizer.json parity — normalizer / pre-tokenizer survey and NFC strategy for commonMain 6 days ago

good first issue research sub-issue skill:numerics size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

👋 New contributors: start here about 2 months ago

documentation help wanted

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 5 · docs] Precision/Recall/F1 — doc partials (math / intuition / examples / references) about 2 months ago

documentation good first issue sub-issue skill:docs size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 3 · native] Precision/Recall/F1 — Kotlin/Native (macOS/Linux) target parity check about 2 months ago

good first issue platform sub-issue coding skill:native size:xs

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 3 · js] Precision/Recall/F1 — JS/Wasm target parity check about 2 months ago

good first issue platform sub-issue coding skill:js size:xs

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 3 · ios] Precision/Recall/F1 — iOS target parity check about 2 months ago

good first issue platform sub-issue coding skill:ios size:xs

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 3 · android] Precision/Recall/F1 — Android target parity check (enable host tests for skainet-backend-cpu) about 2 months ago

good first issue platform sub-issue coding skill:android size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 2 · kotlin-core] F1Score metric about 2 months ago

good first issue training sub-issue coding skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 2 · kotlin-core] Recall metric about 2 months ago

good first issue training sub-issue coding skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 2 · kotlin-core] Precision metric about 2 months ago

good first issue training sub-issue coding skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 2 · kotlin-core] Precision/Recall/F1 — extract Accuracy's class-matching helpers into a shared internal file about 2 months ago

good first issue training sub-issue coding refactor skill:kotlin-core size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Lane 1 · numerics] Precision/Recall/F1 — averaging-mode and zero-division conventions about 2 months ago

good first issue training research sub-issue skill:numerics size:s

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Feature]: Add an Iris dataset provider (and a tabular RawDataset -> Dataset bridge) about 2 months ago

enhancement good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Validate Apple native-cinterop kernels (#958/#959) end-to-end on real iOS/macOS hardware 2 months ago

help wanted platform

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[Feature]: Adopt Kotlin’s default Multiplatform hierarchy template 3 months ago

enhancement good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Replace jackson with kotlinx-schema 3 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Add MIT SPDX headers to one module as a pilot 5 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Migrate for AGP 9: to Android-KMP plugin 8 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Model loading improvements 8 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

MNIST downloader refactoring 8 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Remove WIP vibe code agent files 8 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Add How to contribute docs 9 months ago

documentation good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

ImageNet utilities 9 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

CIFAR-10 9 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

Fashion-MNIST 9 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

[A] Create performance measurment benchmark 9 months ago

good first issue

SKaiNET-developers/SKaiNET

34

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Kotlin

#ai#deep-learning#deep-neural-networks#edge-computing#edge-deep-learning#edge-machine-learning#kotlin#kotlin-multiplatform#ml

SKaiNET-developers/SKaiNET

Open Issues Need Help