ml-jku / SDLG
SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs
☆25Updated 10 months ago
Alternatives and similar repositories for SDLG:
Users that are interested in SDLG are comparing it to the libraries listed below
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆57Updated 10 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- ☆79Updated last year
- Official implementation of "BERTs are Generative In-Context Learners"☆27Updated last month
- ☆120Updated 3 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆111Updated 4 months ago
- ☆52Updated 6 months ago
- LTG-Bert☆32Updated last year
- PyTorch library for Active Fine-Tuning☆64Updated 2 months ago
- Efficient LLM inference on Slurm clusters using vLLM.☆57Updated this week
- Simple Scalable Discrete Diffusion for text in PyTorch☆33Updated 6 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- JAX/Flax implementation of the Hyena Hierarchy☆34Updated last year
- A library for calibrating classifiers and computing calibration metrics☆13Updated 2 years ago
- ☆67Updated 8 months ago
- Learning to Split for Automatic Bias Detection☆48Updated last year
- ☆14Updated last year
- Graph neural networks in JAX.☆67Updated 10 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Simple-to-use scoring function for arbitrarily tokenized texts.☆39Updated 2 months ago
- Efficient Transformers with Dynamic Token Pooling☆60Updated last year
- Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)☆67Updated 8 months ago
- Official implementation of "GPT or BERT: why not both?"☆52Updated last month
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 10 months ago
- ☆54Updated last year
- Quantification of Uncertainty with Adversarial Models☆28Updated last year
- Simple and scalable tools for data-driven pretraining data selection.☆22Updated 2 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆65Updated 7 months ago
- ☆150Updated 8 months ago