Skip to content
View arnavgarg1's full-sized avatar
:bowtie:
:bowtie:
20 followers · 2 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Block or report arnavgarg1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
arnavgarg1/README.md

Hi there, I'm Arnav 👋

I'm a Machine Learning Engineer at Predibase, working on large language models and distributed training. I love working on open-source projects. 🚀

I maintain Ludwig, an open-source toolbox for low-code/no-code deep learning.

Some of my recent work includes:

  1. Co-creating Turbo LoRA, a parameter efficient training method to jointly fine-tune for quality and speculative decoding, improving throughput by upto 3.5x for fine-tuned LoRA adapters. Read More
  2. Developing a mixture of agents synthetic data generation algorithm for supervised instruction tuning that can beat K-shot GPT-4o using just 10 rows of data. Read More
  3. Co-authoring LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report. Read the paper.
  4. Speeding up LLM training by 15x. Read More

You can connect with me on LinkedIn to discuss all things AI 🤖.

If you like my work, feel free to buy me a coffee ☕: https://buymeacoffee.com/arnavgarg


Pinned Loading

  1. ludwig-ai/ludwig ludwig-ai/ludwig Public

    Low-code framework for building custom LLMs, neural networks, and other AI models

    Python 11.3k 1.2k

  2. predibase/lorax predibase/lorax Public

    Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

    Python 2.3k 149