ml-jku / SDLG
SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs
โ25Updated 9 months ago
Alternatives and similar repositories for SDLG:
Users that are interested in SDLG are comparing it to the libraries listed below
- Official implementation of "BERTs are Generative In-Context Learners"โ26Updated 2 weeks ago
- A MAD laboratory to improve AI architecture designs ๐งชโ108Updated 3 months ago
- โ79Updated 11 months ago
- Official implementation of "GPT or BERT: why not both?"โ49Updated 2 weeks ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)โ32Updated 6 months ago
- Discovering Data-driven Hypotheses in the Wildโ65Updated 4 months ago
- โ52Updated 5 months ago
- nanoGPT-like codebase for LLM trainingโ91Updated last week
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amountโฆโ53Updated last year
- LTG-Bertโ31Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jaxโ87Updated 9 months ago
- A fast implementation of T5/UL2 in PyTorch using Flash Attentionโ96Updated 2 weeks ago
- JAX/Flax implementation of the Hyena Hierarchyโ34Updated last year
- PyTorch library for Active Fine-Tuningโ62Updated last month
- โ18Updated 3 weeks ago
- Sparse and discrete interpretability tool for neural networksโ59Updated last year
- โ91Updated last year
- โ150Updated 7 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ103Updated 4 months ago
- some common Huggingface transformers in maximal update parametrization (ยตP)โ80Updated 3 years ago
- Simple-to-use scoring function for arbitrarily tokenized texts.โ38Updated last month
- Modalities, a PyTorch-native framework for distributed and reproducible foundation model training.โ74Updated this week
- CausalGym: Benchmarking causal interpretability methods on linguistic tasksโ41Updated 4 months ago
- โ66Updated 2 years ago
- โ25Updated 7 months ago
- โ34Updated 3 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretabilityโ45Updated last year
- TorchDR - PyTorch Dimensionality Reductionโ98Updated last month
- Triton Implementation of HyperAttention Algorithmโ47Updated last year
- โ51Updated 10 months ago