vignesh's repositories
Optimal-Portfolio-Transactions
We consider the execution of portfolio transactions with the aim of minimizing a combination of risk and transaction costs arising from permanent and temporary market impact. As an example, assume that you have a certain number of stocks that you want to sell within a given time frame. If you place this sell order directly to the market as it is, transaction costs may rise due to temporary market impact. On the other hand, if you split up into pieces in time, cost may rise due to volatility in the stock price
llama-inference
A simple implementation of Llama 1, 2. Llama Architecture built from scratch using PyTorch all the models are built from scratch that includes GQA (Grouped Query Attention) , RoPE (Rotary Positional Embeddings) , RMS Norm, FeedForward Block, Encoder (as this is only for Inferencing the model) , SwiGLU (Activation Function),
Function_calling_LLM
This is an implementation of function calling on your local LLM
infini-transformer
PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)
LexiGenesis
LexiGenesis: Charting the birth and growth of an LLM. From pretraining to fine-tuning and industry deployment, this repo is the epicenter of AI evolution. 🌟
LightAutoML
LAMA - automatic model creation framework
llama-from-scratch
Llama from scratch, or How to implement a paper without crying
llama_index
LlamaIndex (GPT Index) is a data framework for your LLM applications
lloco
The official repo for "LLoCo: Learning Long Contexts Offline"
MicrosoftML-ProjectShowcasing
A repository to keep all open sources projects that created by individuals or study groups of Microsoft ML Scholarship
nerf-pytorch
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
qiskit-honeywell-provider
Qiskit provider for Honeywell backends.
routing-engine
An Open Source routing engine integrated with all the necessary needs to accomidate an routing platform for travel planning, logistics, ride hailing businesses, etc
Transformers
A simple transformer model from paper "Attention is all you need" where data is split to heads which is not efficent compared to
Transformers_from-SCRATCH
A vanilla transformer implementation using pytorch and experimented on deepmind/code_contests dataset
whisper-API
A clean deployment of Whisper API with Docker and FastAPI
zeta
Build high-performance AI models with modular building blocks