Joseph [open/acc] Pollack's picture

Joseph [open/acc] Pollack

Tonic

·

https://discord.gg/qdfnvSPcqP

AI & ML interests

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

Recent Activity

liked a dataset about 16 hours ago

TurkuNLP/finerweb-10bt

liked a Space 3 days ago

benjamin-paine/Lumina-Image-2.0

updated a Space 3 days ago

benjamin-paine/Lumina-Image-2.0

View all activity

Articles

Local AI with Docker's Testcontainers

How to use Instruct Embeddings Correctly

Organizations

Tonic's activity

upvoted a collection 4 days ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 10 items • Updated 4 days ago • 82

upvoted a paper 9 days ago

ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

Paper • 2501.10132 • Published 17 days ago • 17

upvoted a collection 11 days ago

SmolVLM 256M & 500M

Collection for models & demos for even smoller SmolVLM release • 12 items • Updated 11 days ago • 64

upvoted a collection 12 days ago

GTE ModernBERT

GTE Models Based on ModernBERT • 2 items • Updated 13 days ago • 12

upvoted an article 13 days ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Jun 24, 2024

• 183

upvoted an article 17 days ago

Article

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

18 days ago

• 62

upvoted an article 19 days ago

Article

Getting Started With Embeddings

Jun 23, 2022

• 48

upvoted an article 21 days ago

Article

Embodied AI == Unlimited Training Data

By

•

21 days ago

• 3

upvoted a collection 23 days ago

Human-Like LLMs

Human-Like LLMs series. • 5 items • Updated 14 days ago • 12

upvoted 2 collections 24 days ago

Electrical Device Feedback Classification Models

The "Electrical Device Feedback Classification Models" collection contains models trained to classify customer feedback on electrical devices. • 5 items • Updated 29 days ago • 3

TACO Models

This collection contains the best-performing TACO models based on LLaMA-3/Qwen2 and SigLIP/CLIP. • 3 items • Updated Dec 20, 2024 • 8

upvoted a collection 25 days ago

My Loras

loras i've made that are hosted here • 12 items • Updated 19 days ago • 8

upvoted a paper 25 days ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published 26 days ago • 251

upvoted a collection 25 days ago

Sa2VA model zoo

4 items • Updated 19 days ago • 28

upvoted a collection 26 days ago

Deepseek V3 (All Versions)

Deepseek V3 - available in bf16, original, and GGUF formats, with support for 2, 3, 4, 5, 6 and 8-bit quantized versions. • 3 items • Updated about 12 hours ago • 29

upvoted a collection 27 days ago

Cosmos

The collection of Cosmos models • 31 items • Updated 17 days ago • 254

upvoted an article 27 days ago

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By

•

about 1 month ago

• 32

upvoted 2 collections about 1 month ago

QVQ

QVQ: Qwen models for visual reasoning • 7 items • Updated Jan 1 • 43

📐 FineMath

FineMath datasets and ablation models • 14 items • Updated 28 days ago • 19

upvoted a collection about 2 months ago

Falcon3

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters. • 40 items • Updated 26 days ago • 80