Hoptimizer's picture

Hoptimizer

bunnycore

·

SelfishPriority

AI & ML interests

LLM, Text to Image and Video, Love Model Merging

Organizations

None yet

bunnycore's activity

upvoted a collection 1 day ago

OpenCoder

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 4 items • Updated 1 day ago • 33

upvoted a paper about 1 month ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 165

upvoted 2 collections about 1 month ago

ShareGPT Datasets

18 items • Updated 6 days ago • 2

S.T.E.M. - ShargeGPT

Just a collection of some datasets in shareGPT • 16 items • Updated Oct 9 • 3

upvoted a paper about 2 months ago

Improvements to SDXL in NovelAI Diffusion V3

Paper • 2409.15997 • Published Sep 24 • 11

upvoted a collection 2 months ago

LLM For Smartphone

These are some of the best llm that can run on a smartphone. These models go toe-to-toe with much larger models, and are great for use on the go. • 12 items • Updated Oct 8 • 4

upvoted a paper 2 months ago

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 6

upvoted a paper 3 months ago

Scalable Autoregressive Image Generation with Mamba

Paper • 2408.12245 • Published Aug 22 • 23

upvoted 3 collections 3 months ago

Datasets with Educational Values

10 items • Updated Aug 22 • 2

XGen-MM-1 models and datasets

A collection of all XGen-MM (Foundation LMM) models! • 15 items • Updated 5 days ago • 34

Video Generation models

The domain of video generation is booming. Here are the list of selected Open Access video generation (T2V) models. • 14 items • Updated Aug 27 • 12

upvoted 2 papers 3 months ago

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Paper • 2408.08872 • Published Aug 16 • 97

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Paper • 2408.06195 • Published Aug 12 • 61

upvoted a collection 4 months ago

InternLM2.5

14 items • Updated Sep 14 • 70

upvoted a paper 4 months ago

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published Jun 24 • 67

upvoted 5 collections 5 months ago

Gemma 2 Release

15 items • Updated Sep 9 • 193

TTS

3 items • Updated Jun 23 • 2

DPO Datasets

27 items • Updated Aug 15 • 3

ViP-LLaVA

ViP-LLaVA is a novel approach to allow large multimodal models understand arbitrary visual prompts. • 3 items • Updated Mar 25 • 2

Best SDXL Model

6 items • Updated Jun 30 • 2