Tonic (Joseph Pollack)

upvoted a paper about 19 hours ago

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

Paper • 2405.15574 • Published 5 days ago • 41

upvoted a paper 1 day ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published 1 day ago • 31

upvoted a paper 4 days ago

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published 13 days ago • 93

upvoted a collection 6 days ago

RecurrentGemma Release

Collection

6 items • Updated 15 days ago • 19

upvoted a paper 6 days ago

Anchor-based Large Language Models

Paper • 2402.07616 • Published Feb 12 • 2

upvoted a collection 9 days ago

MAmmoTH2

Collection

Scaling up instruction data from the web for to build better LLMs • 11 items • Updated 3 days ago • 6

upvoted a paper 9 days ago

To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency

Paper • 2304.02721 • Published Apr 5, 2023 • 2

upvoted 2 collections 12 days ago

CommonCanvas

Collection

Collection of models trained on the CommonCatalogue datasets • 8 items • Updated 13 days ago • 5

Video-LLaVA 1.0 Model

Collection

a collection of Video-LLaVA 1.0 • 3 items • Updated 6 days ago • 4

upvoted 2 collections 13 days ago

CommonCatalog

Collection

Common Catalog, a dataset with Creative Commons licensed images and machine-generated caption pairs • 8 items • Updated 13 days ago • 7

MADLAD-400

Collection

Models and spaces for MADLAD-400: A Multilingual And Document-Level Large Audited Dataset • 8 items • Updated Nov 14, 2023 • 5

upvoted a collection 15 days ago

Chronos Models

Collection

Chronos: Pretrained (language) models for time series forecasting based on the T5 architecture. • 6 items • Updated Mar 18 • 25

upvoted an article 19 days ago

Article

Speech Synthesis, Recognition, and More With SpeechT5

Feb 8, 2023

• 2

upvoted a collection 19 days ago

Speaker Diarization Datasets

Collection

A collection of speaker diarization datasets compatible with Diarizers. • 6 items • Updated about 1 hour ago • 1

upvoted 2 papers 19 days ago

End-to-end speaker segmentation for overlap-aware resegmentation

Paper • 2104.04045 • Published Apr 8, 2021 • 1

Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation

Paper • 2210.13248 • Published Oct 24, 2022 • 1

upvoted an article 19 days ago

Article

Train custom AI models with the trainer API and adapt them to 🤗

By

•

4 days ago

• 19

upvoted a collection 22 days ago

Granite Code Models

Collection

A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 14 items • Updated 7 days ago • 133

upvoted 2 collections 24 days ago

llama 3 self-align experiments

Collection

Replicating the pipeline for StarCoder-2 Instruct on Llama-3-8B with some tweaks https://huggingface.co/blog/sc2-instruct • 4 items • Updated 20 days ago • 6

Community Tools

Collection

Cool HF tools that I and others at HF work on that I regularly use • 4 items • Updated 8 days ago • 3

upvoted a paper 28 days ago

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published 29 days ago • 41

upvoted a paper about 1 month ago

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

Paper • 2311.05800 • Published Nov 10, 2023 • 2

upvoted a collection about 1 month ago

🦢SWIM-IR Dataset

Collection

29 million Synthetic Wikipedia-based Multilingual Retrieval Training Pairs. • 4 items • Updated Apr 28 • 6

upvoted 2 papers about 1 month ago

PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits

Paper • 2305.02547 • Published May 4, 2023 • 5

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Paper • 2404.03715 • Published Apr 4 • 58

upvoted 2 collections about 1 month ago

Top LLM

Collection

Collection of TOP Open Source LLM • 4 items • Updated 23 days ago • 6

ablation-models

Collection

1.8B models trained on 350BT to compare different pretraining datasets • 7 items • Updated 24 days ago • 20

upvoted a paper about 1 month ago

Generalizable Face Landmarking Guided by Conditional Face Warping

Paper • 2404.12322 • Published Apr 18 • 1

upvoted a collection about 1 month ago

Caduceus

Collection

https://caduceus-dna.github.io/ • 8 items • Updated Apr 19 • 9

upvoted 4 papers about 1 month ago

upvoted 2 collections about 1 month ago

Antidote Project

Collection

Data and models generated within the Antidote Project (https://univ-cotedazur.eu/antidote) • 20 items • Updated 23 days ago • 5

LLM

Collection

14 items • Updated Apr 24 • 1

upvoted 4 papers about 1 month ago

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

Paper • 2206.15076 • Published Jun 30, 2022 • 3

Arcee's MergeKit: A Toolkit for Merging Large Language Models

Paper • 2403.13257 • Published Mar 20 • 17

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 43

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 152

upvoted a collection about 1 month ago

Models - Fintech

Collection

6 items • Updated Apr 17 • 3

upvoted an article about 1 month ago

Article

Custom architectures with HuggingFace 🤗

By

•

Apr 22

• 20

upvoted 2 collections about 1 month ago

WizardLM

Collection

0 items • Updated 21 days ago • 97

Idefics2 🐶

Collection

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated 23 days ago • 82

upvoted a paper about 2 months ago

YOLO-World: Real-Time Open-Vocabulary Object Detection

Paper • 2401.17270 • Published Jan 30 • 30

upvoted 4 collections about 2 months ago

MGM

Collection

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated 26 days ago • 43

Inference Endpoints For Eval Spec. Models

Collection

Models i want to use upstream as part of evaluation libraries then use them to optimize evaluations and downstream applications. • 8 items • Updated Apr 5 • 2

HF-curated models available on Workers AI

Collection

A collection of models curated with Hugging Face that can be run on Cloudflare's Workers AI serverless inference platform. • 15 items • Updated Apr 2 • 48

State-of-the-Art NER models - Keyphrases

Collection

1 item • Updated Feb 27 • 1

upvoted 3 papers about 2 months ago

RED^{rm FM}: a Filtered and Multilingual Relation Extraction Dataset

Paper • 2306.09802 • Published Jun 16, 2023 • 4

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Paper • 2403.18814 • Published Mar 27 • 40

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

Paper • 2404.00399 • Published Mar 30 • 39

upvoted a collection about 2 months ago

Utility

Collection

147 items • Updated 1 day ago • 1

upvoted a paper about 2 months ago

Airavata: Introducing Hindi Instruction-tuned LLM

Paper • 2401.15006 • Published Jan 26 • 3

upvoted 5 collections 3 months ago

Realistic Vision (SD1.5)

Collection

8 items • Updated Dec 4, 2023 • 19

RealVisXL (SDXL)

Collection

12 items • Updated Feb 27 • 28

SambaLingo

Collection

Expert models that adapt Llama2 to a diverse set of languages from around the world. • 27 items • Updated Apr 17 • 34

UDOP

Collection

UDOP is a general multimodal model for document AI • 4 items • Updated 7 days ago • 20

Hub Models

Collection

273 items • Updated 3 days ago • 4

upvoted a paper 3 months ago

Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures

Paper • 2402.05424 • Published Feb 8 • 17

upvoted a collection 3 months ago

💫 StarCoder2

Collection

StarCoder2 models and datasets! • 8 items • Updated Mar 1 • 74

Joseph Pollack

AI & ML interests

Organizations

Tonic's activity

Speech Synthesis, Recognition, and More With SpeechT5

Train custom AI models with the trainer API and adapt them to 🤗

Custom architectures with HuggingFace 🤗