Joseph [open/acc] Pollack's picture

Joseph [open/acc] Pollack

Tonic

·

https://chat.tonic-ai.com

AI & ML interests

🤖Making robots to help people learn things quicker 👩🏻‍🚀🚀

Recent Activity

updated a Space about 4 hours ago

Tonic/Salamandra-7B

updated a Space about 4 hours ago

Tonic/Llava-Video

updated a Space about 4 hours ago

Articles

Local AI with Docker's Testcontainers

How to use Instruct Embeddings Correctly

Organizations

Tonic's activity

upvoted 2 collections 4 days ago

UltraVox Audio Language Model Release 🔊

3 items • Updated 6 days ago • 15

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 7 items • Updated 2 days ago • 35

upvoted an article 8 days ago

Article

Solving NaN Tensors and Pickling Errors in a ZeroGPU Space

By

•

8 days ago

• 3

upvoted 2 collections 21 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 10 items • Updated about 3 hours ago • 172

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 15 days ago • 95

upvoted 2 collections 22 days ago

Dataset Creation

Spaces and utilities for creating datasets and getting them on the Hub • 3 items • Updated 11 days ago • 8

Synthetic Dataset Creation

Spaces focused on generating synthetic datasets • 5 items • Updated 11 days ago • 6

upvoted a collection 27 days ago

MelodyFlow

MelodyFlow: High Fidelity Text-Guided Music Generation and Editing via Single-Stage Flow Matching • 7 items • Updated 29 days ago • 16

upvoted a collection 29 days ago

C4AI Aya 23

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 4 items • Updated Aug 6 • 50

upvoted 4 collections about 1 month ago

Pangea

A Fully Open Multilingual Multimodal LLM for 39 Languages • 18 items • Updated 20 days ago • 17

LayerSkip

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated about 3 hours ago • 43

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 17 days ago • 89

MedEmbed: Embedding Models for Medical Domain

GitHub -> https://github.com/abhinand5/MedEmbed • 4 items • Updated about 1 month ago • 7

upvoted 2 articles about 1 month ago

Article

MedEmbed: Fine-Tuned Embedding Models for Medical / Clinical IR

By

•

Oct 20

• 30

Article

AI is turning nuclear: a review

By

•

Oct 20

• 11

upvoted a paper about 1 month ago

HelpSteer2-Preference: Complementing Ratings with Preferences

Paper • 2410.01257 • Published Oct 2 • 21

upvoted 2 collections about 1 month ago

Biomedical

Models for biomedical research applications, such as radiology report generation and biomedical language understanding. • 9 items • Updated 20 days ago • 4

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 28 days ago • 481

upvoted a paper about 1 month ago

Cognitive Architectures for Language Agents

Paper • 2309.02427 • Published Sep 5, 2023 • 8

upvoted a collection about 2 months ago

LLaVA-Video

Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 6 items • Updated Oct 5 • 53