AxAI (Shikhar Singh)

upvoted 2 articles 13 days ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

13 days ago

• 119

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

Sep 13, 2023

• 6

upvoted a collection 14 days ago

Yi-1.5 (2024/05)

Collection

10 items • Updated 7 days ago • 73

upvoted an article 17 days ago

Article

Optimizing your LLM in production

Sep 15, 2023

• 4

upvoted 4 articles 19 days ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 131

Article

Accelerating Document AI

Nov 21, 2022

• 9

Article

A Dive into Pretraining Strategies for Vision-Language Models

Feb 3, 2023

• 22

Article

Design choices for Vision Language Models in 2024

By

•

Apr 16

• 20

upvoted a paper 19 days ago

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

Paper • 2405.00732 • Published 28 days ago • 113

upvoted 2 articles 21 days ago

Article

SeeMoE: Implementing a MoE Vision Language Model from Scratch

By

•

21 days ago

• 24

Article

Vision Language Models Explained

Apr 11

• 88

upvoted a collection 23 days ago

VILA: On Pre-training for Visual Language Models

Collection

10 items • Updated 21 days ago • 26

upvoted a paper about 1 month ago

MobileSAMv2: Faster Segment Anything to Everything

Paper • 2312.09579 • Published Dec 15, 2023 • 20

upvoted a collection about 1 month ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Apr 18 • 540

upvoted 2 papers 2 months ago

LMDX: Language Model-based Document Information Extraction and Localization

Paper • 2309.10952 • Published Sep 19, 2023 • 61

PERL: Parameter Efficient Reinforcement Learning from Human Feedback

Paper • 2403.10704 • Published Mar 15 • 55

upvoted 2 papers 3 months ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6 • 175

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Paper • 2307.02499 • Published Jul 4, 2023 • 14

upvoted a paper 5 months ago

TinyGSM: achieving >80% on GSM8k with small language models

Paper • 2312.09241 • Published Dec 14, 2023 • 33

upvoted a paper 6 months ago

CogVLM: Visual Expert for Pretrained Language Models

Paper • 2311.03079 • Published Nov 6, 2023 • 19

upvoted 2 collections 7 months ago

OpenChat

Collection

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data • 7 items • Updated Jan 10 • 32

Zephyr 7B

Collection

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated Apr 12 • 138

upvoted a paper 7 months ago

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Paper • 2308.07921 • Published Aug 15, 2023 • 20

upvoted 5 papers 8 months ago

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

Paper • 2310.08491 • Published Oct 12, 2023 • 50

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Paper • 2309.11674 • Published Sep 20, 2023 • 29

Investigating Answerability of LLMs for Long-Form Question Answering

Paper • 2309.08210 • Published Sep 15, 2023 • 11

Multimodal Foundation Models: From Specialists to General-Purpose Assistants

Paper • 2309.10020 • Published Sep 18, 2023 • 39

CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages

Paper • 2309.09400 • Published Sep 17, 2023 • 77

upvoted 2 papers 9 months ago

YaRN: Efficient Context Window Extension of Large Language Models

Paper • 2309.00071 • Published Aug 31, 2023 • 59

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Paper • 2306.16527 • Published Jun 21, 2023 • 42

upvoted 3 papers 10 months ago

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

Paper • 2308.03279 • Published Aug 7, 2023 • 19

Med-Flamingo: a Multimodal Medical Few-shot Learner

Paper • 2307.15189 • Published Jul 27, 2023 • 21

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Paper • 2307.13269 • Published Jul 25, 2023 • 29

upvoted 2 papers 11 months ago

Semantic-SAM: Segment and Recognize Anything at Any Granularity

Paper • 2307.04767 • Published Jul 10, 2023 • 19

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Paper • 2306.14289 • Published Jun 25, 2023 • 15

Shikhar Singh

AI & ML interests

Organizations

AxAI's activity

PaliGemma – Google's Cutting-Edge Open Vision Language Model

Fine-tuning Llama 2 70B using PyTorch FSDP

Yi-1.5 (2024/05)

Optimizing your LLM in production

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Accelerating Document AI

A Dive into Pretraining Strategies for Vision-Language Models

Design choices for Vision Language Models in 2024

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

SeeMoE: Implementing a MoE Vision Language Model from Scratch

Vision Language Models Explained

VILA: On Pre-training for Visual Language Models

MobileSAMv2: Faster Segment Anything to Everything

Meta Llama 3

LMDX: Language Model-based Document Information Extraction and Localization

PERL: Parameter Efficient Reinforcement Learning from Human Feedback

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

TinyGSM: achieving >80% on GSM8k with small language models

CogVLM: Visual Expert for Pretrained Language Models

OpenChat

Zephyr 7B

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Investigating Answerability of LLMs for Long-Form Question Answering

Multimodal Foundation Models: From Specialists to General-Purpose Assistants

CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages

YaRN: Efficient Context Window Extension of Large Language Models

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

Med-Flamingo: a Multimodal Medical Few-shot Learner

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Semantic-SAM: Segment and Recognize Anything at Any Granularity

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications