Reimplementation of https://github.com/montemac/algebraic_value_editing in pure PyTorch for efficiency on large models
☆11Jun 28, 2023Updated 2 years ago
Alternatives and similar repositories for activation_additions_hf
Users that are interested in activation_additions_hf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A how-to for customizing the integration of Braze's SDK☆12Jan 25, 2022Updated 4 years ago
- 삼각형의 실전! Triton☆16Feb 15, 2024Updated 2 years ago
- Algebraic value editing in pretrained language models☆70Nov 1, 2023Updated 2 years ago
- a fast implementation of BM25☆10Sep 15, 2022Updated 3 years ago
- ☆17Jan 4, 2023Updated 3 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Implementation of "Towards Understanding Mixture of Experts in Deep Learning", NeurIPS 2022☆10Jan 6, 2023Updated 3 years ago
- Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.☆10Feb 27, 2024Updated 2 years ago
- Machine learning project using federated learning for text generation☆11May 5, 2024Updated 2 years ago
- [EMNLP2023]: MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control☆12Nov 11, 2023Updated 2 years ago
- A JavaScript project that combines the rhythm gameplay of Dance Dance Revolution with an endless runner.☆12Jul 6, 2017Updated 8 years ago
- ☆19Jun 10, 2024Updated last year
- ☆36Feb 20, 2025Updated last year
- some mixture of experts architecture implementations☆27Mar 22, 2024Updated 2 years ago
- Federated Learning - PyTorch☆15Jun 27, 2021Updated 4 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Inverse transform sampling in Python☆21Jun 19, 2018Updated 7 years ago
- ☆13Nov 11, 2022Updated 3 years ago
- A Neovim Linux plugin to easy encrypt and decrypt your secured directory☆13Jan 28, 2025Updated last year
- Simple example app using Gatsby.js with Purescript☆12Jan 6, 2023Updated 3 years ago
- linear algebra done right in coq☆11Apr 6, 2021Updated 5 years ago
- Official code for the paper Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception. The code is based on t…☆20Aug 5, 2025Updated 9 months ago
- A take on TodoMVC developed using functional effects with @matechs/effect and fp-ts☆15Jan 6, 2023Updated 3 years ago
- A toolbox with the goal of speeding up research on bargaining in MARL (cooperation problems in MARL).☆32Sep 29, 2022Updated 3 years ago
- 自制的爱斯维尔期刊的LaTeX投稿工作流程模板☆21Sep 19, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆67Feb 16, 2023Updated 3 years ago
- Comprehensive API for Nintendo GBA inspired by HAMLib and HELlib.☆32Jan 19, 2026Updated 4 months ago
- The reproduct of the paper - Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction☆21May 29, 2024Updated 2 years ago
- A fully type-safe multi-role communication protocol framework.☆13Nov 21, 2024Updated last year
- Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)☆29Mar 1, 2024Updated 2 years ago
- Transcripts for various Youtube Channels inspired by https://karpathy.ai/lexicap/index.html☆17Nov 14, 2025Updated 6 months ago
- YouTube Assistant☆12May 15, 2023Updated 3 years ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 2024Updated last year
- Content-addressable storage, implemented over pyfilesystem2.☆17Jun 17, 2020Updated 5 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆14Aug 9, 2023Updated 2 years ago
- UPDATE 20210705: Adding ZeroMQ functions in to allow full-duplex comms with deep parts of the hosts' cognitive processes, and expose spe…☆25Jul 8, 2021Updated 4 years ago
- Purely-functional library for the discriminating cryptographer.☆10Dec 12, 2017Updated 8 years ago
- LaunchDarkly Server-Side SDK for Haskell☆15Updated this week
- Federated learning using a mixture of experts☆17Feb 16, 2021Updated 5 years ago
- Well... my dotfiles!☆14May 8, 2026Updated 3 weeks ago
- ☆16Oct 5, 2022Updated 3 years ago