gautierdag / bpeasy
Fast bare-bones BPE for modern tokenizer training
☆154Updated 3 weeks ago
Alternatives and similar repositories for bpeasy:
Users that are interested in bpeasy are comparing it to the libraries listed below
- RuLES: a benchmark for evaluating rule-following in language models☆221Updated last month
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆189Updated 10 months ago
- Extract full next-token probabilities via language model APIs☆241Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆105Updated 5 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆254Updated 9 months ago
- ☆92Updated last year
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆255Updated last year
- A puzzle to learn about prompting☆127Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆123Updated last year
- Sparsify transformers with SAEs and transcoders☆519Updated this week
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 8 months ago
- Draw more samples☆189Updated 10 months ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆82Updated last year
- Simple Transformer in Jax☆136Updated 10 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated 5 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆187Updated 4 months ago
- Scaling Data-Constrained Language Models☆334Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆194Updated 4 months ago
- Understand and test language model architectures on synthetic tasks.☆192Updated last month
- ☆302Updated 10 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆170Updated 3 months ago
- git extension for {collaborative, communal, continual} model development☆211Updated 5 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆96Updated last month
- Experiments for efforts to train a new and improved t5☆77Updated last year
- ☆128Updated 3 weeks ago
- Accelerate, Optimize performance with streamlined training and serving options with JAX.☆263Updated this week
- Website for hosting the Open Foundation Models Cheat Sheet.☆267Updated this week
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- An interactive exploration of Transformer programming.☆262Updated last year
- code for training & evaluating Contextual Document Embedding models☆180Updated this week