ml-jku / SDLGLinks
SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs
☆25Updated last year
Alternatives and similar repositories for SDLG
Users that are interested in SDLG are comparing it to the libraries listed below
Sorting:
- ☆81Updated last year
- Official implementation of "BERTs are Generative In-Context Learners"☆28Updated 3 months ago
- Simple and scalable tools for data-driven pretraining data selection.☆24Updated 2 weeks ago
- Simple Scalable Discrete Diffusion for text in PyTorch☆33Updated 9 months ago
- ☆68Updated 10 months ago
- ☆53Updated 8 months ago
- Efficient LLM inference on Slurm clusters using vLLM.☆65Updated last week
- ☆54Updated 2 years ago
- ☆125Updated 5 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆42Updated last month
- Modalities, a PyTorch-native framework for distributed and reproducible foundation model training.☆81Updated this week
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Official implementation of "GPT or BERT: why not both?"☆53Updated 2 weeks ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆58Updated last year
- Evaluation of neuro-symbolic engines☆35Updated 10 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated 2 years ago
- Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning☆33Updated 5 months ago
- LTG-Bert☆33Updated last year
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Interpretating the latent space representations of attention head outputs for LLMs☆33Updated 10 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- A library for calibrating classifiers and computing calibration metrics☆13Updated 2 years ago
- A mechanistic approach for understanding and detecting factual errors of large language models.☆46Updated 11 months ago
- Discovering Data-driven Hypotheses in the Wild☆94Updated 2 weeks ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 9 months ago
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 8 months ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Updated 2 years ago
- ☆35Updated 2 years ago