-
Max Planck Institute for Software Systems: MPI SWS
- Delhi
-
01:54
(UTC +05:30) - https://aflah02.github.io/
- @Aflah02101
Lists (23)
Sort Name ascending (A-Z)
Evals
Fun Project Ideas
Hate Speech
Interview Prep
Kernels
Lexicons
LLM API Powertools
LLM Deployment
LLM-RL
LM Eval
Local LLMs
ML PowerTools
Multimodal
Pretraining Dataset
Python Tooling
RAG
RIdeas
Streamlit Components
Style Transfer
BaselinesSynthetic Data
Telemetry
TTS
Websites
Stars
- All languages
- Assembly
- Astro
- Batchfile
- BibTeX Style
- C
- C#
- C++
- CSS
- Cuda
- Cython
- D
- Dart
- Dockerfile
- Fortran
- Go
- Groovy
- HTML
- Java
- JavaScript
- Jsonnet
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lua
- Luau
- MDX
- MLIR
- Makefile
- Markdown
- Mathematica
- Mojo
- NSIS
- Nim
- Nix
- Odin
- PLpgSQL
- Perl
- Python
- R
- Rocq Prover
- Roff
- Ruby
- Rust
- SCSS
- SWIG
- Scala
- Shell
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- Typst
- Vue
- Zig
- reStructuredText
Tooling for exact and MinHash deduplication of large-scale text datasets
Verify Precision of all Kimi K2 API Vendor
A Zola theme embracing minimalism, focusing on clean CSS while steering clear of resource-heavy JavaScript. Immerse yourself in a seamless user experience, powered by lightning-fast load times. ⚡
A minimal and clean CSS Classless framework, designed to provide a lightweight and elegant foundation for web development. Keep your projects streamlined and stylish with a framework that doesn't s…
"Paper2Slides: From Paper to Presentation in One Click"
flex-block-attn: an efficient block sparse attention computation library
Earth system foundation model data, training, and eval
Fully Open Language Models with Stellar Performance
A framework for efficient model inference with omni-modality models
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Super basic implementation (gist-like) of RLMs with REPL environments.
[Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques
Clean Jupyter notebooks for version control. Remove metadata, outputs, and execution counts with Git and pre-commit support.