vgel / repeng
A library for making RepE control vectors
☆528Updated last week
Alternatives and similar repositories for repeng:
Users that are interested in repeng are comparing it to the libraries listed below
- Sparse autoencoders☆407Updated this week
- Visualize the intermediate output of Mistral 7B☆333Updated 11 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆298Updated 3 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆214Updated 8 months ago
- Stop messing around with finicky sampling parameters and just use DRµGS!☆336Updated 7 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆704Updated last year
- ☆413Updated last year
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆162Updated last week
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆372Updated 7 months ago
- utilities for decoding deep representations (like sentence embeddings) back to text☆760Updated this week
- Draw more samples☆182Updated 6 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆191Updated 3 weeks ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated 8 months ago
- ☆250Updated this week
- ☆493Updated 4 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 7 months ago
- Automatically evaluate your LLMs in Google Colab☆575Updated 8 months ago
- ☆484Updated last month
- smolLM with Entropix sampler on pytorch☆147Updated 2 months ago
- Neural Search☆349Updated 7 months ago
- Extract full next-token probabilities via language model APIs☆230Updated 10 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆605Updated last month
- Erasing concepts from neural representations with provable guarantees☆219Updated last month
- Low-Rank adapter extraction for fine-tuned transformers models☆165Updated 8 months ago
- batched loras☆336Updated last year
- A bagel, with everything.☆315Updated 9 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆426Updated 4 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆273Updated 2 months ago
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆459Updated 9 months ago