dvruette / concept-guidance
Code accompanying the paper "A Language Model's Guide Through Latent Space". It contains functionality for training and using concept vectors that control the behavior of LLMs at inference time.
☆19Updated last year
Alternatives and similar repositories for concept-guidance:
Users that are interested in concept-guidance are comparing it to the libraries listed below
- Code for☆27Updated 4 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- ☆21Updated 4 months ago
- Latent Diffusion Language Models☆68Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆27Updated 7 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- Code for experiments on self-prediction as a way to measure introspection in LLMs☆13Updated 4 months ago
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆33Updated 6 months ago
- Code for the paper "Function-Space Learning Rates"☆19Updated 3 weeks ago
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆31Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated 3 weeks ago
- Implementation of Spectral State Space Models☆16Updated last year
- ☆22Updated last year
- ☆63Updated 7 months ago
- ☆33Updated 10 months ago
- LLM training in simple, raw C/CUDA☆14Updated 5 months ago
- Minimum Description Length probing for neural network representations☆19Updated 3 months ago
- ☆27Updated last year
- Simple repository for training small reasoning models☆27Updated 3 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆43Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 11 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- ☆33Updated 8 months ago
- A repository for research on medium sized language models.☆76Updated 11 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated this week
- PyTorch interface for TrueGrad Optimizers☆41Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Understanding how features learned by neural networks evolve throughout training☆34Updated 6 months ago
- ☆53Updated last year