wolosonovich (Jason Wolosonovich)

upvoted a paper 21 days ago

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published 22 days ago • 76

upvoted 2 articles about 1 month ago

Article

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

By

•

Aug 22

• 12

Article

Welcome FalconMamba: The first strong attention-free 7B model

Aug 12

• 98

upvoted 2 papers about 2 months ago

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Paper • 2408.03910 • Published Aug 7 • 15

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

Paper • 2408.00690 • Published Aug 1 • 21

upvoted an article 2 months ago

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 64

upvoted a paper 2 months ago

E5-V: Universal Embeddings with Multimodal Large Language Models

Paper • 2407.12580 • Published Jul 17 • 38

upvoted an article 2 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 244

upvoted a paper 2 months ago

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Paper • 2407.09025 • Published Jul 12 • 123

upvoted an article 3 months ago

Article

Announcing New Hugging Face and Keras NLP integration

Jul 10

• 29

upvoted 2 papers 3 months ago

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

Paper • 2407.00402 • Published Jun 29 • 22

GEB-1.3B: Open Lightweight Large Language Model

Paper • 2406.09900 • Published Jun 14 • 19

upvoted 3 papers 4 months ago

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Paper • 2406.02657 • Published Jun 4 • 36

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Paper • 2405.11157 • Published May 18 • 25

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

Paper • 2405.11582 • Published May 19 • 12

upvoted 3 papers 6 months ago

TnT-LLM: Text Mining at Scale with Large Language Models

Paper • 2403.12173 • Published Mar 18 • 19

Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU

Paper • 2403.06504 • Published Mar 11 • 53

Chronos: Learning the Language of Time Series

Paper • 2403.07815 • Published Mar 12 • 45

upvoted 4 papers 7 months ago

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Paper • 2403.07816 • Published Mar 12 • 39

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Paper • 2403.03950 • Published Mar 6 • 13

User-LLM: Efficient LLM Contextualization with User Embeddings

Paper • 2402.13598 • Published Feb 21 • 18

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21 • 110

upvoted a collection 7 months ago

Gemma release

Collection

Groups the Gemma models released by the Google team. • 40 items • Updated Jul 31 • 325

upvoted 4 papers 7 months ago

Learning to Learn Faster from Human Feedback with Language Model Predictive Control

Paper • 2402.11450 • Published Feb 18 • 20

upvoted 6 papers 8 months ago

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Paper • 2402.04291 • Published Feb 6 • 48

Scaling Laws for Downstream Task Performance of Large Language Models

Paper • 2402.04177 • Published Feb 6 • 17

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Paper • 2402.01739 • Published Jan 29 • 26

Repeat After Me: Transformers are Better than State Space Models at Copying

Paper • 2402.01032 • Published Feb 1 • 22

ReFT: Reasoning with Reinforced Fine-Tuning

Paper • 2401.08967 • Published Jan 17 • 27

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

Paper • 2401.12954 • Published Jan 23 • 28

upvoted a paper 9 months ago

LLM Augmented LLMs: Expanding Capabilities through Composition

Paper • 2401.02412 • Published Jan 4 • 36

upvoted 2 papers 12 months ago

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Paper • 2309.14509 • Published Sep 25, 2023 • 17

Retentive Network: A Successor to Transformer for Large Language Models

Paper • 2307.08621 • Published Jul 17, 2023 • 170

Jason Wolosonovich

AI & ML interests

Organizations

wolosonovich's activity

OLMoE: Open Mixture-of-Experts Language Models

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

Welcome FalconMamba: The first strong attention-free 7B model

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

Docmatix - a huge dataset for Document Visual Question Answering

E5-V: Universal Embeddings with Multimodal Large Language Models

SmolLM - blazingly fast and remarkably powerful

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Announcing New Hugging Face and Keras NLP integration

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

GEB-1.3B: Open Lightweight Large Language Model

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Towards Modular LLMs by Building and Reusing a Library of LoRAs

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

TnT-LLM: Text Mining at Scale with Large Language Models

Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU

Chronos: Learning the Language of Time Series

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

User-LLM: Efficient LLM Contextualization with User Embeddings

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Gemma release

Learning to Learn Faster from Human Feedback with Language Model Predictive Control

Tandem Transformers for Inference Efficient LLMs

Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model

Mixtures of Experts Unlock Parameter Scaling for Deep RL

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Scaling Laws for Downstream Task Performance of Large Language Models

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Repeat After Me: Transformers are Better than State Space Models at Copying

ReFT: Reasoning with Reinforced Fine-Tuning

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

LLM Augmented LLMs: Expanding Capabilities through Composition

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Retentive Network: A Successor to Transformer for Large Language Models