Arnav Garg's picture

9 9 1

Arnav Garg

arnavgrg

·

https://www.predibase.com

AI & ML interests

Large Language Models, Distributed Training and Inference

Recent Activity

published a dataset about 2 months ago

predibase/wordle-sft

new activity about 2 months ago

predibase/wordle-grpo:[bot] Conversion to Parquet

updated a dataset about 2 months ago

predibase/wordle-sft

View all activity

Organizations

arnavgrg's activity

upvoted a paper 5 months ago

The Lessons of Developing Process Reward Models in Mathematical Reasoning

Paper • 2501.07301 • Published Jan 13 • 98

upvoted a paper 12 months ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published Jun 25, 2024 • 98

upvoted an article about 1 year ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

By

•

May 28, 2024

• 225

upvoted a paper about 1 year ago

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

Paper • 2405.00732 • Published Apr 29, 2024 • 122

upvoted an article about 1 year ago

Article

Welcome Llama 3 - Meta's new open LLM

By

and 4 others •

Apr 18, 2024

• 290

upvoted 3 collections about 1 year ago

Dequantized Base Models

Dequantized (fp16) versions of nf4 quantized base models for faster inference. • 40 items • Updated Dec 13, 2024 • 1

Customer Support LoRA Adapters

Fine-Tuned LoRA adapters for customer support. Fine-tune using Ludwig: pbase.ai/ludwig-cs; Fine-tune using Predibase: pbase.ai/cs-predibase-full • 3 items • Updated Apr 26, 2024 • 1

Lora Land - 27 High-Quality LoRA Adapters

27 Fine-tuned LoRA Adapters using Mistral-7B. Try them here: https://predibase.com/lora-land • 27 items • Updated Apr 26, 2024 • 5

upvoted a paper about 1 year ago

QLoRA: Efficient Finetuning of Quantized LLMs

Paper • 2305.14314 • Published May 23, 2023 • 53