Tonic (Joseph Pollack)

upvoted an article 1 day ago

Article

LLM Inference at scale with TGI

By

•

2 days ago

• 4

upvoted 4 papers 2 days ago

SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

Paper • 2405.07518 • Published May 13 • 24

upvoted an article 2 days ago

Article

Getty Images Brings High-Quality, Commercially Safe Dataset to Hugging Face

By

•

2 days ago

• 8

upvoted a collection 4 days ago

Yi-Coder

Collection

4 items • Updated 4 days ago • 25

upvoted a paper 6 days ago

InkubaLM: A small language model for low-resource African languages

Paper • 2408.17024 • Published 10 days ago • 9

upvoted a collection 10 days ago

Qwen2-VL

Collection

Vision-language model series based on Qwen2 • 11 items • Updated 4 days ago • 86

upvoted a paper 11 days ago

Enhancing Training Efficiency Using Packing with Flash Attention

Paper • 2407.09105 • Published Jul 12 • 11

upvoted an article 18 days ago

Article

XetHub is joining Hugging Face!

Aug 8

• 73

upvoted a collection 21 days ago

🪐 SmolLM

Collection

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated 22 days ago • 165

upvoted a collection 24 days ago

DeepSeek-Prover

Collection

DeepSeek-V1-and-V1.5-Series • 7 items • Updated 23 days ago • 13

upvoted an article 24 days ago

Article

The Workflow of PEFT

By

•

26 days ago

• 19

upvoted a collection 25 days ago

synthetic-data-generation-demos

Collection

A collection of demos for various approaches to synthetic data generation • 4 items • Updated Jun 25 • 13

upvoted an article 25 days ago

Article

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Aug 22, 2023

• 21

upvoted a collection 26 days ago

InternLM2.5

Collection

13 items • Updated Aug 6 • 66

upvoted an article 27 days ago

Article

Tool Use, Unified

28 days ago

• 45

upvoted 2 papers about 1 month ago

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Paper • 2408.01800 • Published Aug 3 • 74

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Paper • 2408.02900 • Published Aug 6 • 25

upvoted an article about 1 month ago

Article

The case for specialized pre-training: ultra-fast foundation models for dedicated tasks

By

•

Aug 4

• 24

upvoted a paper about 1 month ago

EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks

Paper • 2402.00892 • Published Jan 31 • 12

upvoted an article about 1 month ago

Article

RAG chatbot using llama3

By

•

Jul 7

• 62

upvoted a paper about 1 month ago

SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound

Paper • 2406.06612 • Published Jun 6 • 14

upvoted 2 collections about 1 month ago

SEE-2-SOUND

Collection

4 items • Updated Jul 6 • 4

Probably function calling datasets

Collection

Created using the https://huggingface.co/spaces/librarian-bots/dataset-column-search-api Space. • 39 items • Updated Jul 17 • 34

upvoted 2 articles about 1 month ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23

• 42

Article

Local AI with Docker's Testcontainers

By

•

Aug 3

• 5

upvoted a collection about 1 month ago

Palmyra (Writer license)

Collection

Palmyra LLMs under Writer license https://writer.com/legal/open-model-license/ • 8 items • Updated 22 days ago • 6

upvoted 2 articles about 1 month ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30

• 49

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29

• 181

upvoted a collection about 1 month ago

Granite Time Series Models

Collection

A collection of time series models trained by IBM licensed under Apache 2.0 license. • 4 items • Updated Jul 19 • 10

upvoted a paper about 1 month ago

The Importance of Online Data: Understanding Preference Fine-tuning via Coverage

Paper • 2406.01462 • Published Jun 3 • 6

upvoted an article about 2 months ago

Article

Announcing Finance Commons and the Bad Data Toolbox: Pioneering Open Data and Advanced Document Processing

By

•

Jul 19

• 17

upvoted a collection about 2 months ago

Finance Commons

Collection

A large collection of multimodal financial documents in open data. • 7 items • Updated Jul 17 • 3

upvoted 6 papers about 2 months ago

E5-V: Universal Embeddings with Multimodal Large Language Models

Paper • 2407.12580 • Published Jul 17 • 38

LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Paper • 2407.12772 • Published Jul 17 • 32

Patch-Level Training for Large Language Models

Paper • 2407.12665 • Published Jul 17 • 16

GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression

Paper • 2407.12077 • Published Jul 16 • 52

Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models

Paper • 2407.12327 • Published Jul 17 • 75

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Paper • 2407.12784 • Published Jul 17 • 48

upvoted an article about 2 months ago

Article

Train a Llama model from scratch

By

•

Jul 29

• 37

upvoted 2 collections about 2 months ago

Embedding Model Datasets

Collection

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 67 items • Updated Jul 3 • 61

Magpie-Qwen2 Datasets

Collection

Dataset built with Qwen2 72B and Qwen2 7B. • 6 items • Updated Jul 27 • 10

upvoted an article about 2 months ago

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Jul 16

• 30

upvoted 4 papers about 2 months ago

Qwen Technical Report

Paper • 2309.16609 • Published Sep 28, 2023 • 34

BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning

Paper • 2206.08657 • Published Jun 17, 2022 • 2

ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning

Paper • 2306.00103 • Published May 31, 2023 • 1

Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15 • 153

upvoted 3 articles 2 months ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By

•

Jul 5

• 72

Article

Accelerating Protein Language Model ProtST on Intel Gaudi 2

Jul 3

• 2

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27

• 115

upvoted 3 collections 2 months ago

LLM Compiler

Collection

Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. • 4 items • Updated Jun 27 • 145

Gemma 2 Release

Collection

14 items • Updated Jul 31 • 163

Probably DPO datasets

Collection

A collection of datasets that probably support DPO • 146 items • Updated Jun 26 • 11

upvoted 2 papers 3 months ago

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5 • 67

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Paper • 2312.08935 • Published Dec 14, 2023 • 4

upvoted an article 3 months ago

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 60

upvoted a paper 3 months ago

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Paper • 2406.09406 • Published Jun 13 • 13

upvoted a collection 3 months ago

Instruction Pre-Training

Collection

8 items • Updated Jun 21 • 25

Joseph Pollack

AI & ML interests

Articles

Local AI with Docker's Testcontainers

How to use Instruct Embeddings Correctly

Organizations

Tonic's activity

LLM Inference at scale with TGI

Getty Images Brings High-Quality, Commercially Safe Dataset to Hugging Face

XetHub is joining Hugging Face!

The Workflow of PEFT

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Tool Use, Unified

The case for specialized pre-training: ultra-fast foundation models for dedicated tasks

RAG chatbot using llama3

🪆 Introduction to Matryoshka Embedding Models

Local AI with Docker's Testcontainers

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Announcing Finance Commons and the Bad Data Toolbox: Pioneering Open Data and Advanced Document Processing

Train a Llama model from scratch

How we leveraged distilabel to create an Argilla 2.0 Chatbot

ColPali: Efficient Document Retrieval with Vision Language Models 👀

Accelerating Protein Language Model ProtST on Intel Gaudi 2

Welcome Gemma 2 - Google's new open LLM

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints