-
Carnegie Mellon University
- Yaoundé
- https://baimamboukar.dev
- https://orcid.org/0009-0000-2115-4031
- @baimamboukarr
- baimamboukar
- in/baimamboukar
- https://medium.com/@baimamboukar
Highlights
Lists (9)
Sort Name ascending (A-Z)
- All languages
- Assembly
- Astro
- Batchfile
- C
- C#
- C++
- CMake
- CSS
- Clojure
- Dart
- EJS
- Elixir
- Go
- HCL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- Nix
- Objective-C
- PHP
- Perl
- PowerShell
- Processing
- Python
- QML
- R
- ReScript
- Rich Text Format
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smarty
- Solidity
- Swift
- TeX
- TypeScript
- Vue
Starred repositories
Sparsify transformers with SAEs and transcoders
Open source replication of Anthropic's Crosscoders for Model Diffing
open source interpretability platform 🧠
A sparse autoencoder I trained on Mistral's open source 7b model!
Training Sparse Autoencoders on Language Models
GraphRAG-powered knowledge graph that maps AI policies across Africa and suggests frameworks for countries without one
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Exa MCP for web search and web crawling!
Token-efficient CLI for AI agents to read, write, and collaborate on Google Docs & Drive.
Autonomous research loops on GPU pods with Claude Code
bloom - evaluate any behavior immediately 🌸🌱
Inference API for many LLMs and other useful tools for empirical research
The nnsight package enables interpreting and manipulating the internals of deep learned models.
ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
Inspect: A framework for large language model evaluations
An alignment auditing agent capable of quickly exploring alignment hypothesis
APPS: Automated Programming Progress Standard (NeurIPS 2021)