tnlin (Tony Lin)

upvoted a paper 2 days ago

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published 4 days ago • 69

upvoted a paper 7 days ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published 13 days ago • 75

upvoted a collection 19 days ago

Awesome SFT datasets

Collection

A curated list of interesting datasets to fine-tune language models with. • 43 items • Updated Apr 12 • 99

upvoted a paper 22 days ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 80

upvoted a paper about 1 month ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 91

upvoted a collection 2 months ago

Self-evolution of LLMs

Collection

3 items • Updated Apr 23 • 1

upvoted 6 papers 2 months ago

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Paper • 2404.13208 • Published Apr 19 • 38

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 240

Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs

Paper • 2310.19347 • Published Oct 30, 2023 • 1

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

Paper • 2403.02178 • Published Mar 4 • 1

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use

Paper • 2312.04455 • Published Dec 7, 2023 • 1

A Survey on Self-Evolution of Large Language Models

Paper • 2404.14387 • Published Apr 22 • 2

upvoted 3 papers 3 months ago

upvoted a paper 4 months ago

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Paper • 2402.01739 • Published Jan 29 • 26

upvoted a paper 5 months ago

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

Paper • 2401.12474 • Published Jan 23 • 33

upvoted a paper 7 months ago

GAIA: a benchmark for General AI Assistants

Paper • 2311.12983 • Published Nov 21, 2023 • 175

upvoted a collection 8 months ago

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 • 141

upvoted a paper 8 months ago

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Paper • 2310.20624 • Published Oct 31, 2023 • 12

upvoted 4 papers 9 months ago

UniSA: Unified Generative Framework for Sentiment Analysis

Paper • 2309.01339 • Published Sep 4, 2023 • 1

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

Paper • 2305.13040 • Published May 22, 2023 • 1

Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models

Paper • 2309.12940 • Published Sep 22, 2023 • 2

Constructive Large Language Models Alignment with Diverse Feedback

Paper • 2310.06450 • Published Oct 10, 2023 • 1

Tony Lin

AI & ML interests

Organizations

tnlin's activity

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Awesome SFT datasets

LoRA Learns Less and Forgets Less

What matters when building vision-language models?

Self-evolution of LLMs

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use

A Survey on Self-Evolution of Large Language Models

Best Practices and Lessons Learned on Synthetic Data for Language Models

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

LLM Agent Operating System

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

GAIA: a benchmark for General AI Assistants

Zephyr 7B

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

UniSA: Unified Generative Framework for Sentiment Analysis

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models

Constructive Large Language Models Alignment with Diverse Feedback