Modalities / modalitiesLinks
Modalities, a PyTorch-native framework for distributed and reproducible foundation model training.
☆78Updated last week
Alternatives and similar repositories for modalities
Users that are interested in modalities are comparing it to the libraries listed below
Sorting:
- Efficient LLM inference on Slurm clusters using vLLM.☆65Updated last week
- nanoGPT-like codebase for LLM training☆98Updated last month
- some common Huggingface transformers in maximal update parametrization (µP)☆81Updated 3 years ago
- A case study of efficient training of large language models using commodity hardware.☆69Updated 2 years ago
- Simple-to-use scoring function for arbitrarily tokenized texts.☆41Updated 4 months ago
- ☆37Updated last year
- Utilities for the HuggingFace transformers library☆68Updated 2 years ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆74Updated 7 months ago
- Code for Zero-Shot Tokenizer Transfer☆133Updated 5 months ago
- A framework for few-shot evaluation of autoregressive language models.☆104Updated 2 years ago
- Supercharge huggingface transformers with model parallelism.☆77Updated 8 months ago
- SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs☆25Updated last year
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆105Updated 3 months ago
- Understand and test language model architectures on synthetic tasks.☆218Updated 2 weeks ago
- ☆54Updated 2 years ago
- LM engine is a library for pretraining/finetuning LLMs☆57Updated this week
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated 10 months ago
- ☆74Updated last year
- Experiments for efforts to train a new and improved t5☆77Updated last year
- ☆53Updated 8 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Pretraining Efficiently on S2ORC!☆164Updated 8 months ago
- Code for the MTEB Arena☆20Updated 9 months ago
- ☆57Updated last week
- ☆166Updated last year
- ☆97Updated 4 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆63Updated 7 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆122Updated 6 months ago
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆40Updated 3 months ago