takara.ai

company

Verified

https://takara.ai

takara-ai

Activity Feed Request to join this org

AI & ML interests

GenAI, Diffusion, LLM's and State of the Art Solutions.

Recent Activity

aldigobbler updated a model 6 days ago

takara-ai/SwarmFormer-Sentiment-Small

aldigobbler updated a model 6 days ago

takara-ai/SwarmFormer-Sentiment-Base

takarajordan published a dataset about 2 months ago

takara-ai/rand-1m-multimodal

View all activity

takara-ai 's collections 15

Image Datasets

Our frontier vision data!

takara-ai/image_captions

Viewer • Updated Feb 11 • 1.07M • 957 • 20
takara-ai/MovieStills_Captioned_SmolVLM

Viewer • Updated Feb 25 • 74.9k • 155

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

Paper • 2411.14974 • Published Nov 22, 2024 • 16

Synthetic Data Generation

A collection of research papers, datasets and models focused on data generation by machines.

proj-persona/PersonaHub

Viewer • Updated Mar 4 • 375k • 6.45k • 598

Foundational Vision

microsoft/Florence-2-large

Image-Text-to-Text • Updated Dec 8, 2024 • 1.02M • 1.58k

Model Security

Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks

Paper • 2407.02855 • Published Jul 3, 2024 • 13

Small LLM’s

HuggingFaceTB/SmolLM-135M-Instruct

Text Generation • 0.1B • Updated Sep 4, 2024 • 20.3k • 119
HuggingFaceTB/SmolLM-360M-Instruct

Text Generation • 0.4B • Updated Aug 18, 2024 • 14.8k • 83
HuggingFaceTB/SmolLM-1.7B-Instruct

Text Generation • 2B • Updated Aug 18, 2024 • 7.16k • 115

MultiModal

Running on Zero

772

772

Florence 2

📉

Analyze images to generate captions, detect objects, or perform OCR

Audio

MuCodec: Ultra Low-Bitrate Music Codec

Paper • 2409.13216 • Published Sep 20, 2024 • 24

SwarmFormer

Our collection of our frontier SwarmFormer architecture models.

takara-ai/SwarmFormer-Sentiment-Small

Updated 6 days ago • 19 • 5
takara-ai/SwarmFormer-Sentiment-Base

Updated 6 days ago • 10 • 6

Medical

Teach Multimodal LLMs to Comprehend Electrocardiographic Images

Paper • 2410.19008 • Published Oct 21, 2024 • 24

LLM Performance

Papers, tools and techniques on maximising LLM performance both in production and in training.

facebook/multi-token-prediction

Updated Jun 18, 2024 • 369
Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Paper • 2407.04620 • Published Jul 5, 2024 • 34

LLM Scaling

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages

Paper • 2407.05975 • Published Jul 8, 2024 • 38
Associative Recurrent Memory Transformer

Paper • 2407.04841 • Published Jul 5, 2024 • 37

VLM Performance

Vision language models are blind

Paper • 2407.06581 • Published Jul 9, 2024 • 83

Large LLM's

meta-llama/Llama-3.1-405B-Instruct

Text Generation • 406B • Updated Sep 25, 2024 • 24.3k • • 573

Autonomous Agents

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper • 2408.06292 • Published Aug 12, 2024 • 126
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents

Paper • 2407.01511 • Published Jul 1, 2024