custom-transformer

A PyTorch-based transformer library for language modeling and automatic speech recognition (ASR). Includes both a numpy-based multi-head attention implementation (mytorch) and a full PyTorch transformer toolkit (transformerlib) with training, decoding, and data loading utilities.

Installation

pip install custom-transformer

Features

`mytorch` — NumPy Attention Primitives

Pure numpy implementations for educational and prototyping purposes:

Linear — fully-connected layer with forward and backward passes
Softmax — numerically stable softmax activation
ScaledDotProductAttention — attention mechanism with optional masking
MultiHeadAttention — multi-head attention with split/concat head logic

from mytorch.nn import MultiHeadAttention
mha = MultiHeadAttention(d_model=512, num_heads=8)

`transformerlib` — PyTorch Transformer Toolkit

Full-featured transformer models and training infrastructure:

Models

DecoderOnlyTransformer — GPT-style causal language model
EncoderDecoderTransformer — encoder-decoder for sequence-to-sequence tasks (e.g., ASR)
Pre-LN architecture with sinusoidal positional encoding
Weight tying, layer dropout, and mixed precision support
from_pretrained_decoder for initializing encoder-decoder models from pretrained decoder weights

Data

LMDataset — text dataset with tokenization, SOS/EOS framing, and collation
ASRDataset — speech dataset with filterbank features, global MVN normalization, and SpecAugment
H4Tokenizer — BPE tokenizer wrapper (char, 1k, 5k, 10k vocab sizes included)

Training

LMTrainer — language model training with gradient accumulation, mixed precision, and WandB logging
ASRTrainer — ASR training with CTC + cross-entropy joint loss
ProgressiveTrainer — curriculum learning with gradual layer unfreezing and data subsetting

Decoding

SequenceGenerator — greedy search, beam search, and nucleus sampling
Language model shallow fusion for ASR recognition

Quick Start

from transformerlib.model import DecoderOnlyTransformer

model = DecoderOnlyTransformer(
    num_layers=6,
    d_model=512,
    num_heads=8,
    d_ff=2048,
    dropout=0.1,
    max_len=512,
    num_classes=10000
)

from transformerlib.model import EncoderDecoderTransformer

model = EncoderDecoderTransformer(
    num_encoder_layers=6,
    num_decoder_layers=6,
    d_model=512,
    num_heads=8,
    d_ff=2048,
    dropout=0.1,
    max_len=512,
    num_classes=1000,
    feat_dim=80
)

Architecture

mytorch/
  nn/
    linear.py
    activation.py
    scaled_dot_product_attention.py
    multi_head_attention.py

transformerlib/
  model/        — masks, positional encoding, sublayers, encoder/decoder layers, transformers
  data/         — tokenizer, LM dataset, ASR dataset
  trainers/     — base trainer, LM trainer, ASR trainer, progressive trainer
  decoding/     — sequence generator (greedy, beam, sampling)
  utils/        — optimizer and LR scheduler factories

Requirements

Python >= 3.9
PyTorch >= 2.0
torchaudio
numpy, tqdm, wandb, torchmetrics, tokenizers, pandas, matplotlib

License

MIT

Metadata

Release files for custom-transformer 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for custom-transformer 0.1.0
File	Interpreter	ABI	Platform	Reset
custom_transformer-0.1.0-cp313-cp313-win_amd64.whl 1.0 MB Feb 10, 2026	CPython 3.13	CPython 3.13	Windows x86-64	Details
custom_transformer-0.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 6.4 MB Feb 10, 2026	CPython 3.13	CPython 3.13	Linux glibc 2.17+ x86-64	Details
custom_transformer-0.1.0-cp313-cp313-macosx_10_13_universal2.whl 2.1 MB Feb 10, 2026	CPython 3.13	CPython 3.13	macOS 10.13+ universal2 (ARM64, x86-64)	Details
custom_transformer-0.1.0-cp312-cp312-win_amd64.whl 1.0 MB Feb 10, 2026	CPython 3.12	CPython 3.12	Windows x86-64	Details
custom_transformer-0.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 6.6 MB Feb 10, 2026	CPython 3.12	CPython 3.12	Linux glibc 2.17+ x86-64	Details
custom_transformer-0.1.0-cp312-cp312-macosx_10_13_universal2.whl 2.1 MB Feb 10, 2026	CPython 3.12	CPython 3.12	macOS 10.13+ universal2 (ARM64, x86-64)	Details
custom_transformer-0.1.0-cp311-cp311-win_amd64.whl 1.1 MB Feb 10, 2026	CPython 3.11	CPython 3.11	Windows x86-64	Details
custom_transformer-0.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 6.4 MB Feb 10, 2026	CPython 3.11	CPython 3.11	Linux glibc 2.17+ x86-64	Details
custom_transformer-0.1.0-cp311-cp311-macosx_10_9_universal2.whl 2.1 MB Feb 10, 2026	CPython 3.11	CPython 3.11	macOS 10.9+ universal2 (ARM64, x86-64)	Details
custom_transformer-0.1.0-cp310-cp310-win_amd64.whl 1.1 MB Feb 10, 2026	CPython 3.10	CPython 3.10	Windows x86-64	Details
custom_transformer-0.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 6.0 MB Feb 10, 2026	CPython 3.10	CPython 3.10	Linux glibc 2.17+ x86-64	Details
custom_transformer-0.1.0-cp310-cp310-macosx_10_9_universal2.whl 2.1 MB Feb 10, 2026	CPython 3.10	CPython 3.10	macOS 10.9+ universal2 (ARM64, x86-64)	Details

Total release size: 38.1 MB

Release files / custom_transformer-0.1.0-cp313-cp313-win_amd64.whl

Download URL	custom_transformer-0.1.0-cp313-cp313-win_amd64.whl
Size	1.0 MB
Tags	CPython 3.13 Windows x86-64
SHA-256 checksum How to use checksums	`e7be9e7b93604f7e07bc1ab60c5c29854bf6c3c54c6d5210b1a19bad0cea22d4`
BLAKE2b-256 checksum How to use checksums	`55b72a9dfa7df64db5f40b2453a77eb30f73a8acbc74347b197688053db6ecb2`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp313-cp313-win_amd64.whl
SHA-256 checksum: e7be9e7b93604f7e07bc1ab60c5c29854bf6c3c54c6d5210b1a19bad0cea22d4 Verifying attestations

Release files / custom_transformer-0.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL	custom_transformer-0.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size	6.4 MB
Tags	CPython 3.13 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`ac2c498ede2db9e6c55be60e6017a60b094f060508bf9b0b96cae62abde6e51d`
BLAKE2b-256 checksum How to use checksums	`4f1e829fc134260a87f4c2c3b69da67991b65baed83f5ca0bf6c09fa41441755`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
SHA-256 checksum: ac2c498ede2db9e6c55be60e6017a60b094f060508bf9b0b96cae62abde6e51d Verifying attestations

Release files / custom_transformer-0.1.0-cp313-cp313-macosx_10_13_universal2.whl

Download URL	custom_transformer-0.1.0-cp313-cp313-macosx_10_13_universal2.whl
Size	2.1 MB
Tags	CPython 3.13 macOS 10.13+ universal2 (ARM64, x86-64)
SHA-256 checksum How to use checksums	`e78e8ebc41d253b8f996a0d0fabae6e4069478866a25ede6aa24df58058f860c`
BLAKE2b-256 checksum How to use checksums	`692054d2f006759a15041b7b8a31be88d92b2ddec5f439fbda1d365184f1d557`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp313-cp313-macosx_10_13_universal2.whl
SHA-256 checksum: e78e8ebc41d253b8f996a0d0fabae6e4069478866a25ede6aa24df58058f860c Verifying attestations

Release files / custom_transformer-0.1.0-cp312-cp312-win_amd64.whl

Download URL	custom_transformer-0.1.0-cp312-cp312-win_amd64.whl
Size	1.0 MB
Tags	CPython 3.12 Windows x86-64
SHA-256 checksum How to use checksums	`65c6b0f33c039ea53cc1070e874b6e67a5772f631acd7a295c1979837722f09b`
BLAKE2b-256 checksum How to use checksums	`2e546ffa6eb8589ce15cbe8279d196149044cf563b179afe44faf77b92c1aace`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp312-cp312-win_amd64.whl
SHA-256 checksum: 65c6b0f33c039ea53cc1070e874b6e67a5772f631acd7a295c1979837722f09b Verifying attestations

Release files / custom_transformer-0.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL	custom_transformer-0.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size	6.6 MB
Tags	CPython 3.12 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`d456f7ac73cec1584ccceb746a93d6d75aad77dcc7b6c0e4e682640c8bb7242b`
BLAKE2b-256 checksum How to use checksums	`c5e43e1d22164783e7f4dee4d25e85a139d672293bee68605835eef806accf5f`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
SHA-256 checksum: d456f7ac73cec1584ccceb746a93d6d75aad77dcc7b6c0e4e682640c8bb7242b Verifying attestations

Release files / custom_transformer-0.1.0-cp312-cp312-macosx_10_13_universal2.whl

Download URL	custom_transformer-0.1.0-cp312-cp312-macosx_10_13_universal2.whl
Size	2.1 MB
Tags	CPython 3.12 macOS 10.13+ universal2 (ARM64, x86-64)
SHA-256 checksum How to use checksums	`5a94ed782428d43e65ba1624042ff955eeb34b4a13c684b7d85d43baf179110c`
BLAKE2b-256 checksum How to use checksums	`8c045c366669128b8cd5ea47527cc3f785f592f336150a1852ca1b5c4c0321f8`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp312-cp312-macosx_10_13_universal2.whl
SHA-256 checksum: 5a94ed782428d43e65ba1624042ff955eeb34b4a13c684b7d85d43baf179110c Verifying attestations

Release files / custom_transformer-0.1.0-cp311-cp311-win_amd64.whl

Download URL	custom_transformer-0.1.0-cp311-cp311-win_amd64.whl
Size	1.1 MB
Tags	CPython 3.11 Windows x86-64
SHA-256 checksum How to use checksums	`028ebbf76e09c349252185523e93e46b6c1d64e323b948bcc1321ad91d332c7c`
BLAKE2b-256 checksum How to use checksums	`208ed16619b522b47f31e4582bad1fcb2121fc0edecf891c0768a056973903e6`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp311-cp311-win_amd64.whl
SHA-256 checksum: 028ebbf76e09c349252185523e93e46b6c1d64e323b948bcc1321ad91d332c7c Verifying attestations

Release files / custom_transformer-0.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL	custom_transformer-0.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size	6.4 MB
Tags	CPython 3.11 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`023c465c9847e010e85a306fe6a2eb96c1bcc3dbc07aaee75e8b0786c1c1e98f`
BLAKE2b-256 checksum How to use checksums	`da46b446b7a300fb13c88b2bd20f954b8fb150d3ca7f9e45328171fb227afe39`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
SHA-256 checksum: 023c465c9847e010e85a306fe6a2eb96c1bcc3dbc07aaee75e8b0786c1c1e98f Verifying attestations

Release files / custom_transformer-0.1.0-cp311-cp311-macosx_10_9_universal2.whl

Download URL	custom_transformer-0.1.0-cp311-cp311-macosx_10_9_universal2.whl
Size	2.1 MB
Tags	CPython 3.11 macOS 10.9+ universal2 (ARM64, x86-64)
SHA-256 checksum How to use checksums	`dcec103ce64af1ec90cf2a5eeb0eac9f4de9ae8edf6ea2995f662286d7f28332`
BLAKE2b-256 checksum How to use checksums	`bc234576257bce46a04d8415c4026950897a4fbd48fb06b9af4c7e3e6ae29128`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp311-cp311-macosx_10_9_universal2.whl
SHA-256 checksum: dcec103ce64af1ec90cf2a5eeb0eac9f4de9ae8edf6ea2995f662286d7f28332 Verifying attestations

Release files / custom_transformer-0.1.0-cp310-cp310-win_amd64.whl

Download URL	custom_transformer-0.1.0-cp310-cp310-win_amd64.whl
Size	1.1 MB
Tags	CPython 3.10 Windows x86-64
SHA-256 checksum How to use checksums	`7429d7d1b051e84f7bef807b600534359e3991319b0e0f998400af149af60cf9`
BLAKE2b-256 checksum How to use checksums	`66e8d37e48022222fda59a29933c9849dcd37d32b4a2c9587c9392a3843259bd`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp310-cp310-win_amd64.whl
SHA-256 checksum: 7429d7d1b051e84f7bef807b600534359e3991319b0e0f998400af149af60cf9 Verifying attestations

Release files / custom_transformer-0.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL	custom_transformer-0.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size	6.0 MB
Tags	CPython 3.10 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`a2721f066ff65e25d23b6b15c608be500ba3242ff47dfc7de2cbb4c0361d73e7`
BLAKE2b-256 checksum How to use checksums	`18595ecf580c4c8b351d6954a2b621a7bbed24962786d90ef8f2c5388eb23743`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
SHA-256 checksum: a2721f066ff65e25d23b6b15c608be500ba3242ff47dfc7de2cbb4c0361d73e7 Verifying attestations

Release files / custom_transformer-0.1.0-cp310-cp310-macosx_10_9_universal2.whl

Download URL	custom_transformer-0.1.0-cp310-cp310-macosx_10_9_universal2.whl
Size	2.1 MB
Tags	CPython 3.10 macOS 10.9+ universal2 (ARM64, x86-64)
SHA-256 checksum How to use checksums	`bbfd620e1d098e905715cbca765983eba485d59e03938db89f7f8d80d31ac59a`
BLAKE2b-256 checksum How to use checksums	`a30e220b11c357c302733f81486ea545528e0be34f37f3ad4bf74ef063e86cc2`
Upload date	Feb 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kkipngenokoech/custom-transformer
Publishing commit: github.com/kkipngenokoech/custom-transformer/tree/ee8e750d7f85c70fe5513a9aa68da07da4e6252e

Workflow

Publishing configuration: github.com/kkipngenokoech/custom-transformer/blob/ee8e750d7f85c70fe5513a9aa68da07da4e6252e/.github/workflows/publish.yml
Publishing logs: github.com/kkipngenokoech/custom-transformer/actions/runs/21858772939/attempts/1

Artifact

Subject: custom_transformer-0.1.0-cp310-cp310-macosx_10_9_universal2.whl
SHA-256 checksum: bbfd620e1d098e905715cbca765983eba485d59e03938db89f7f8d80d31ac59a Verifying attestations

Release history Release notifications | RSS feed

This release

0.1.0 This release

Feb 10, 2026 12 release files

custom-transformer 0.1.0

custom-transformer

Installation

Features

mytorch — NumPy Attention Primitives

transformerlib — PyTorch Transformer Toolkit

Quick Start

Architecture

Requirements

License

Key dates

1 maintainer

License

Requires

Provides Extra

Metadata

Key dates

1 maintainer

License

Requires

Provides Extra

Release files for custom-transformer 0.1.0

Built distributions (wheels)

Release files / custom_transformer-0.1.0-cp313-cp313-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp313-cp313-macosx_10_13_universal2.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp312-cp312-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp312-cp312-macosx_10_13_universal2.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp311-cp311-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp311-cp311-macosx_10_9_universal2.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / custom_transformer-0.1.0-cp310-cp310-win_amd64.whl

Provenance

PyPI Publish Attestation

`mytorch` — NumPy Attention Primitives

`transformerlib` — PyTorch Transformer Toolkit