D.E.V.S.

All

6 repositories

Shredword
Public
Fast & efficient BPE tokenizer written in C & python for LLM training
tokenizer tokenization sub-words tiktoken llm-training
C++
•
Apache License 2.0
•0•1•0•0•Updated Jan 4, 2026Jan 4, 2026
Axon
Public
Lightweight tensor library for deep learning model low-latency inference (cpu only)
numpy array array-manipulations matmul
C++
•
Apache License 2.0
•1•0•3•0•Updated Dec 14, 2025Dec 14, 2025
.github
Public
JavaScript
•0•0•0•0•Updated Dec 4, 2025Dec 4, 2025
CookbookLLM
Public
Cookbook to produce ML models from scratch with working examples & dataset pipelines
Python
•
MIT License
•0•0•2•0•Updated Oct 24, 2025Oct 24, 2025
Biosaic
Public
KMer level tokenizer for DNA & Proteins sequences
encoder tokenizer kmer protein-structure-prediction tokenizaiton alphafold3 dna-tokenizer protein-tokenizer kmer-encoding bio-tokenizer
Python
•
Apache License 2.0
•0•0•0•0•Updated Jul 16, 2025Jul 16, 2025
EnigmaDataset
Public
Dataset generation pipeline for Enigma2 using NCBI database
biopython ncbi-genbank ncbi data-pipeline ncbi-database alphafold2 dna-database dna-database-pipline
Python
•
MIT License
•0•0•0•0•Updated Jun 7, 2025Jun 7, 2025