apoorvumang
Research Scientist, Adobe Research India. Working on NLP and Multi-modal content
Adobe ResearchBangalore
apoorvumang's Stars
minusxai/minusx
MinusX is an AI Data Scientist for Analytics Apps you already use and love. Currently it supports Jupyter, Metabase, Google Sheets & Posthog.
public-apis/public-apis
A collective list of free APIs
danmarshall/google-font-to-svg-path
Create an SVG path from a Google font
protagolabs/odyssey-math
ZhengxiangShi/InstructionModelling
[NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"
naklecha/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
uma-pi1/kgt5-context
thomasgauthier/LoRD
Low-Rank adapter extraction for fine-tuned transformers models
nuwandavek/justplotme
suno-ai/bark
🔊 Text-Prompted Generative Audio Model
pratyushasharma/laser
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
nosiu/InstantID-faceswap
InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥
tyxsspa/AnyText
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
Amal-David/whatsapp-llm
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
instantX-research/InstantID
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
huggingface/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
instructor-ai/instructor
structured outputs for llms
flowdriveai/flowpilot
flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines.
RayVentura/ShortGPT
🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation
google-research-datasets/QuoteSum
QuoteSum is a textual QA dataset containing Semi-Extractive Multi-source Question Answering (SEMQA) examples written by humans, based on Wikipedia passages.
VikParuchuri/marker
Convert PDF to markdown + JSON quickly with high accuracy
tencent-ailab/IP-Adapter
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
ggerganov/llama.cpp
LLM inference in C/C++
FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
project-miracl/hagrid
A Human-LLM Collaborative Dataset for Generative Information-seeking with Attribution
guoyww/AnimateDiff
Official implementation of AnimateDiff.
google/prompt-to-prompt
cocktailpeanut/dalai
The simplest way to run LLaMA on your local machine
minimaxir/sdxl-experiments
Jupyter Notebooks for experimenting with Stable Diffusion XL 1.0