AT&Dev's picture

AT&Dev

AtAndDev

·

AI & ML interests

LLMs, Self-Improvement, Alignment, DPO, SFT, Unsloth

Organizations

AtAndDev's activity

upvoted a paper about 1 month ago

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4 • 70

upvoted a collection about 1 month ago

Load 4bit models 4x faster

Native bitsandbytes 4bit pre quantized models • 16 items • Updated 20 days ago • 20

upvoted 2 papers about 2 months ago

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Paper • 2401.01335 • Published Jan 2 • 61

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12 • 54

upvoted 2 collections about 2 months ago

Hermes

Nous' Flagship LLM Series • 20 items • Updated 3 days ago • 79

👑 Monarch

Family of 7B models that combine excellent reasoning and conversational abilities. • 7 items • Updated Mar 22 • 9

upvoted 3 papers 2 months ago

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 41

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 116

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Paper • 2401.04398 • Published Jan 9 • 18

upvoted a paper 7 months ago

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Paper • 2308.05374 • Published Aug 10, 2023 • 23

upvoted a paper 8 months ago

Flamingo: a Visual Language Model for Few-Shot Learning

Paper • 2204.14198 • Published Apr 29, 2022 • 13

upvoted 2 papers 9 months ago

StarCoder: may the source be with you!

Paper • 2305.06161 • Published May 9, 2023 • 26

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

Paper • 2307.15063 • Published Jul 27, 2023 • 15