RandallBalestriero / SplineLLMLinks
☆16Updated 2 years ago
Alternatives and similar repositories for SplineLLM
Users that are interested in SplineLLM are comparing it to the libraries listed below
Sorting:
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- Understanding how features learned by neural networks evolve throughout training☆40Updated last year
- Quantification of Uncertainty with Adversarial Models☆29Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- The Energy Transformer block, in JAX☆62Updated last year
- The data and the PyTorch implementation for the models and experiments in the paper "Language Model Decoding as Likelihood–Utility Alignm…☆14Updated 2 years ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆13Updated 2 years ago
- ☆36Updated 3 years ago
- Minimum Description Length probing for neural network representations☆20Updated 10 months ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- Code for "The Expressive Power of Low-Rank Adaptation".☆20Updated last year
- ☆14Updated 3 years ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- 📰 Computing the information content of trained neural networks☆22Updated 4 years ago
- A centralized place for deep thinking code and experiments☆87Updated 2 years ago
- ☆30Updated 2 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆16Updated 4 years ago
- Official code for the paper: "Metadata Archaeology"☆19Updated 2 years ago
- JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"☆19Updated 2 years ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆28Updated last year
- ☆45Updated 2 years ago
- Llemma formal2formal (tactic prediction) theorem proving experiments☆20Updated 2 years ago
- Logic Explained Networks is a python repository implementing explainable-by-design deep learning models.☆53Updated 2 years ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated 2 years ago
- ZeroC is a neuro-symbolic method that trained with elementary visual concepts and relations, can zero-shot recognize and acquire more com…☆33Updated 2 years ago
- Google Research☆46Updated 3 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆38Updated 3 years ago
- Deep Networks Grok All the Time and Here is Why☆38Updated last year
- ☆72Updated last year
- This is the code repository associated with the paper "Abstractors and relational cross-attention: An inductive bias for explicit relati…☆21Updated last year