kuprel / minbpe-pytorchLinks
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization, with PyTorch/CUDA
☆39Updated last year
Alternatives and similar repositories for minbpe-pytorch
Users that are interested in minbpe-pytorch are comparing it to the libraries listed below
Sorting:
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- ☆131Updated last year
- Full finetuning of large language models without large memory requirements☆94Updated last year
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆38Updated 2 years ago
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆201Updated last month
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- utilities for loading and running text embeddings with onnx☆44Updated 3 weeks ago
- inference code for mixtral-8x7b-32kseqlen☆101Updated last year
- GPU accelerated client-side embeddings for vector search, RAG etc.☆65Updated last year
- a small code base for training large models☆310Updated 4 months ago
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated last month
- GPU-targeted vendor-agnostic AI library for Windows, and Mistral model implementation.☆58Updated last year
- Inference of Mamba models in pure C☆191Updated last year
- ☆35Updated 2 years ago
- ☆156Updated 2 years ago
- Python bindings for ggml☆146Updated last year
- WebGPU LLM inference tuned by hand☆151Updated 2 years ago
- NLP with Rust for Python 🦀🐍☆64Updated 3 months ago
- run paligemma in real time☆132Updated last year
- Tree-based indexes for neural-search☆32Updated last year
- Simple high-throughput inference library☆127Updated 3 months ago
- ☆39Updated 2 years ago
- Lightweight tools for quick and easy LLM demo's☆28Updated 11 months ago
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- Chat Markup Language conversation library☆55Updated last year
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆126Updated 4 months ago
- ☆39Updated last year
- Experiments for efforts to train a new and improved t5☆76Updated last year
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆180Updated last month