sankeerthrao
Founder, CEO @Stealth x-Google Research Scientist Ph.D. in ML @ UC San Diego Undergrad in EE @ IIT Bombay
Google ResearchSan Francisco
Pinned Repositories
agi-house-hackathon
alignment-handbook
Robust recipes for to align language models with human and AI preferences
chatgpt-retrieval-plugin
cog_stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
ControlNet
Let us control diffusion models!
langchain
⚡ Building applications with LLMs through composability ⚡
live-streaming-demo
Use D-ID's live streaming API to stream a talking presenter
llama
Inference code for LLaMA models
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
skript
PyPI package to let users run bash scripts via natural language.
sankeerthrao's Repositories
sankeerthrao/skript
PyPI package to let users run bash scripts via natural language.
sankeerthrao/flax
Flax is a neural network library for JAX that is designed for flexibility.
sankeerthrao/OLMo
Modeling, training, eval, and inference code for OLMo
sankeerthrao/OLMo-Eval
Evaluation suite for LLMs
sankeerthrao/open-instruct
sankeerthrao/optax
Optax is a gradient processing and optimization library for JAX.
sankeerthrao/seqax
seqax = sequence modeling + JAX
sankeerthrao/serl
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
sankeerthrao/visionOS
Playing around with visionOS
sankeerthrao/cookbook
A collection of guides and examples for the Gemini API.
sankeerthrao/dm-haiku
JAX-based neural network library
sankeerthrao/drools
Drools is a rule engine, DMN engine and complex event processing (CEP) engine for Java.
sankeerthrao/executorch
On-device AI across mobile, embedded and edge for PyTorch
sankeerthrao/firecrawl
🔥 Turn entire websites into LLM-ready markdown
sankeerthrao/gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
sankeerthrao/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
sankeerthrao/llama3
The official Meta Llama 3 GitHub site
sankeerthrao/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
sankeerthrao/magentic
Seamlessly integrate LLMs as Python functions
sankeerthrao/minbpe
Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
sankeerthrao/objax
sankeerthrao/ollama
Get up and running with Llama 3, Mistral, Gemma, and other large language models.
sankeerthrao/open-gpu-kernel-modules
NVIDIA Linux open GPU with P2P support
sankeerthrao/openai-assistants-quickstart
OpenAI Assistants API quickstart with Next.js.
sankeerthrao/OpenGrip
a simple, low cost, robotics gripper
sankeerthrao/RingAttention
Transformers with Arbitrarily Large Context
sankeerthrao/ROCm
AMD ROCm™ Software - GitHub Home
sankeerthrao/scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
sankeerthrao/surya
OCR and line detection in 90+ languages
sankeerthrao/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.