Moshe Wasserblat's picture

3 4 6

Moshe Wasserblat

moshew

·

AI & ML interests

NLP Efficiency, Sentiment Analysis, Few-shot learning, Distillation

Articles

Universal Assisted Generation: Faster Decoding with Any Assistant Model

Faster Assisted Generation with Dynamic Speculation

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake

CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

SetFit: Efficient Few-Shot Learning Without Prompts

Organizations

moshew's activity

upvoted a paper 2 months ago

FastDraft: How to Train Your Draft

Paper • 2411.11055 • Published Nov 17, 2024 • 10

upvoted a paper 5 months ago

CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity

Paper • 2404.10513 • Published Apr 16, 2024 • 2

upvoted a paper 6 months ago

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

Paper • 2408.02545 • Published Aug 5, 2024 • 36

upvoted a paper 8 months ago

Distributed Speculative Inference of Large Language Models

Paper • 2405.14105 • Published May 23, 2024 • 16