AI & Model Weights
Modern machine learning serialization, quantized inference weights, and tensor container specifications with zero-upload header parsing.
GGUF (GGML Universal File Format)
Self-contained binary model weight format for llama.cpp and local LLM inference engines, storing architecture KV metadata, BPE vocabulary, and quantized tensor blocks in a single mmap-ready file.
NumPy Array Binary Format
Simple, mmap-friendly binary representation of a single homogeneous dense tensor with an explicit ASCII header dictionary describing dtype, byte order, and shape.
NumPy Zipped Array Archive
ZIP container bundling multiple named NumPy `.npy` tensor arrays, widely used for embeddings, calibration datasets, and JAX/MLX checkpoints.
PyTorch Model & Tensor Checkpoint
Default PyTorch `torch.save()` archive wrapping a Python Pickle instruction stream (`data.pkl`) alongside raw tensor storage files inside a ZIP container.