Rishabh's repositories
FourCastNet_gil
Mechanistic Interpretability for Weather Modeing using Vision Transformers
climate_stylegan
stylegan_on_climate_data
CUDA_Lectures
Material for cuda lectures to understand coding in cuda
CUDA_tutorial_flash_attention
https://twitter.com/hyhieu226/status/1787968359285539267
e2e-llm-workflows
End-to-End LLM Guide
earth2mip_gi
earth2mip gilbreth this time with correct runing and experiemnts
equinox
Better version of jax, Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
FairVis
FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
Finetuning_jamba
AI21 model finetuning
fsdp_qlora_answer
Training LLMs with QLoRA + FSDP
gemini_cookbook
A collection of guides and examples for the Gemini API.
jax_transformer
simple implementation of jax transformer with clear maths
large_scale_diskvectorindex
𝐒𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐒𝐞𝐚𝐫𝐜𝐡 𝐨𝐧 𝟏𝟎𝟎𝐌 𝐝𝐨𝐜𝐬 - 𝐖𝐢𝐭𝐡 𝟏𝟎𝟎𝐌𝐁 𝐨𝐟 𝐌𝐞𝐦𝐨𝐫𝐲
llama3_jailbreak
A trivial programmatic Llama 3 jailbreak
llm_inference_optimization
An implementation of bucketMul LLM inference using compressed row matrix
llm_mlops_complete_guide
🤖 LLM Twin Course: Building Your Production-Ready AI Replica | An End-to-End Framework for Production-Ready LLM Systems by Building Your LLM Twin | WIP...
LLM_prompts
JAILBREAK PROMPTS FOR ALL MAJOR AI MODELS
Machine-Learning-Interviews
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
MOE_from_scratch
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
professional-programming
A collection of learning resources for curious software engineers
pytorch_fundamentals
The Fundamentals of Modern Deep Learning with PyTorch by rasbt
pytorch_subclasses
Tensor subclasses in PyTorch
rasbt_LLM_workshop
A 4-hour coding workshop to understand how LLMs are implemented and used by rasbt
similarity_dist_optimized
Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, and C, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-512 and Arm NEON & SVE 📐
Transformer-Puzzles
Puzzles for exploring transformers
Transformers_Are_What_You_Dont_Need
The best repository showing why transformers don’t work in time series forecasting and showcasing the best SOTA non transformer models.
Triton-Puzzles
Puzzles for learning Triton CUDA lang
visualizing_nn_jax
A JAX research toolkit for building, editing, and visualizing neural networks.