gautierdag / bpeasy
Fast bare-bones BPE for modern tokenizer training
☆154Updated last month
Alternatives and similar repositories for bpeasy:
Users that are interested in bpeasy are comparing it to the libraries listed below
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆255Updated last year
- A puzzle to learn about prompting☆127Updated last year
- ☆92Updated last year
- RuLES: a benchmark for evaluating rule-following in language models☆223Updated 2 months ago
- Extract full next-token probabilities via language model APIs☆242Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆189Updated 11 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆255Updated 9 months ago
- A comprehensive deep dive into the world of tokens☆222Updated 10 months ago
- Understand and test language model architectures on synthetic tasks.☆195Updated 2 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated 6 months ago
- Annotated version of the Mamba paper☆483Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆105Updated this week
- Website for hosting the Open Foundation Models Cheat Sheet.☆267Updated 2 weeks ago
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆198Updated last year
- JAX implementation of the Llama 2 model☆218Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 9 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆569Updated this week
- ☆217Updated 9 months ago
- Normalized Transformer (nGPT)☆174Updated 5 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆272Updated 10 months ago
- ☆130Updated last month
- ☆301Updated 10 months ago
- code for training & evaluating Contextual Document Embedding models☆183Updated 2 weeks ago
- An extension of the nanoGPT repository for training small MOE models.☆138Updated last month
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆129Updated 5 months ago
- Deep learning library implemented from scratch in numpy. Mixtral, Mamba, LLaMA, GPT, ResNet, and other experiments.☆51Updated last year
- Simple Transformer in Jax☆136Updated 10 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- A repository for research on medium sized language models.☆495Updated last week
- Highly commented implementations of Transformers in PyTorch☆136Updated last year