Tonic (Joseph Pollack)

upvoted an article 2 days ago

Article

Speech Synthesis, Recognition, and More With SpeechT5

Feb 8, 2023

• 2

upvoted a collection 2 days ago

Speaker Diarization Datasets

Collection

A collection of speaker diarization datasets compatible with Diarizers. • 4 items • Updated 10 days ago • 1

upvoted 2 papers 2 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 2 days ago

Article

Adapt any model to the trainer API and to 🤗

By

•

2 days ago

• 7

upvoted a collection 5 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. • 10 items • Updated about 16 hours ago • 106

upvoted 2 collections 7 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 3 days ago • 5

Community Tools

Collection

Cool HF tools that I and others at HF work on that I regularly use • 3 items • Updated Sep 8, 2023 • 3

upvoted a paper 11 days ago

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published 12 days ago • 37

upvoted a paper 13 days 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 13 days ago

🦢SWIM-IR Dataset

Collection

29 million Synthetic Wikipedia-based Multilingual Retrieval Training Pairs. • 4 items • Updated 14 days ago • 6

upvoted 2 papers 14 days 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 • 57

upvoted a collection 14 days ago

Top LLM

Collection

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

upvoted a collection 16 days ago

ablation-models

Collection

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

upvoted a paper 16 days ago

Generalizable Face Landmarking Guided by Conditional Face Warping

Paper • 2404.12322 • Published 24 days ago • 1

upvoted a collection 17 days ago

Caduceus

Collection

https://caduceus-dna.github.io/ • 8 items • Updated 23 days ago • 8

upvoted 4 papers 19 days ago

upvoted 2 collections 19 days ago

Antidote Project

Collection

Data and models generated within the Antidote Project (https://univ-cotedazur.eu/antidote) • 20 items • Updated 6 days ago • 5

LLM

Collection

14 items • Updated 18 days ago • 1

upvoted 2 papers 19 days 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 • 16

upvoted 2 papers 25 days ago

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 41

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 152

upvoted a collection 25 days ago

Models - Fintech

Collection

6 items • Updated 25 days ago • 3

upvoted an article 25 days ago

Article

Custom architectures with HuggingFace 🤗

By

•

20 days ago

• 20

upvoted 2 collections 26 days ago

WizardLM

Collection

0 items • Updated 3 days ago • 95

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 6 days ago • 68

upvoted a paper about 1 month ago

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

Paper • 2401.17270 • Published Jan 30 • 29

upvoted 4 collections about 1 month ago

MGM

Collection

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated 9 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 • 45

State-of-the-Art NER models - Keyphrases

Collection

1 item • Updated Feb 27 • 1

upvoted 3 papers about 1 month 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 • 37

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 1 month ago

Utility

Collection

136 items • Updated 1 day ago • 1

upvoted a paper about 1 month ago

Airavata: Introducing Hindi Instruction-tuned LLM

Paper • 2401.15006 • Published Jan 26 • 3

upvoted 5 collections 2 months ago

Realistic Vision (SD1.5)

Collection

8 items • Updated Dec 4, 2023 • 18

RealVisXL (SDXL)

Collection

12 items • Updated Feb 27 • 26

SambaLingo

Collection

Expert models that adapt Llama2 to a diverse set of languages from around the world. • 27 items • Updated 24 days ago • 34

UDOP

Collection

UDOP is a general multimodal model for document AI • 4 items • Updated 3 days ago • 19

Hub Models

Collection

263 items • Updated 2 days ago • 4

upvoted a paper 2 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 2 months ago

💫 StarCoder2

Collection

StarCoder2 models and datasets! • 8 items • Updated Mar 1 • 72

upvoted a paper 2 months ago

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Paper • 2402.10176 • Published Feb 15 • 32

upvoted a paper 3 months ago

An Interactive Agent Foundation Model

Paper • 2402.05929 • Published Feb 8 • 24

upvoted 2 collections 3 months ago

matlok - Python Src Code Datasets (base)

Collection

Python code from leading AI research and tools repositories • 2 items • Updated Feb 8 • 1

matlok - Python Code Instruction Datasets

Collection

Python Alpaca instructions from leading AI research and tools repositories - focus is on "Manager level" understanding atm • 4 items • Updated Feb 12 • 1

upvoted a paper 4 months ago

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

Paper • 2310.00274 • Published Sep 30, 2023 • 2

upvoted 3 collections 4 months ago

AudioVideo

Collection

7 items • Updated 16 days ago • 2

ZeroGPU Spaces

Collection

ZeroGPU Spaces made by the community • 15 items • Updated 10 days ago • 89

Segment Anything Model

Collection

This collection contains models and demos of SAM and it's smaller friends. • 17 items • Updated Mar 11 • 6

upvoted a paper 5 months ago

VideoLCM: Video Latent Consistency Model

Paper • 2312.09109 • Published Dec 14, 2023 • 21

upvoted 2 collections 5 months ago

🎦🔀 Useful Tiny Video Converters

Collection

All spaces made to convert a video (of GIFs) to anything useful in your pipelines • 5 items • Updated Feb 20 • 5

File names and splits

Collection

8 datasets showcase the diversity of splits configuration on HuggingFace. See docs: https://huggingface.co/docs/hub/datasets-file-names-and-splits. • 8 items • Updated Nov 22, 2023 • 4

upvoted a paper 6 months ago

Prompt Engineering a Prompt Engineer

Paper • 2311.05661 • Published Nov 9, 2023 • 18

Joseph Pollack

AI & ML interests

Organizations

Tonic's activity

Speech Synthesis, Recognition, and More With SpeechT5

Adapt any model to the trainer API and to 🤗

Custom architectures with HuggingFace 🤗