Joe Hirst's picture

20 55

Joe Hirst

joehirstdev

·

AI & ML interests

Multimodal AI

Organizations

upvoted an article 4 months ago

Article

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

Aug 9

•

47

upvoted a collection 9 months ago

Gemma 3 Release

28 items • Updated Aug 11 • 553

upvoted 2 articles 10 months ago

Article

Remote VAEs for decoding with Inference Endpoints 🤗

Feb 24

•

41

Article

Welcome to Inference Providers on the Hub 🔥

+5

Jan 28

•

490

upvoted a collection 11 months ago

DeepSeek-R1

10 items • Updated 15 days ago • 821

upvoted a paper over 1 year ago

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

Paper • 2104.04045 • Published Apr 8, 2021 • 2

upvoted a collection over 1 year ago

Training Datasets

A collection of pseudo-labelled datasets used to train the Distil-Whisper model. • 9 items • Updated Mar 21, 2024 • 14

upvoted 4 articles over 1 year ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

+6

Jul 23, 2024

•

241

Article

Introducing TextImage Augmentation for Document Images

+1

Aug 6, 2024

•

33

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

+3

May 24, 2023

•

171

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Aug 17, 2022

•

118

upvoted 2 collections over 1 year ago

Llama 3.1 GPTQ, AWQ, and BNB Quants

Optimised Quants for high-throughput deployments! Compatible with Transformers, TGI & VLLM 🤗 • 9 items • Updated Sep 26, 2024 • 57

Gemma 2 2B Release

The 2.6B parameter version of Gemma 2. • 6 items • Updated Jul 10 • 81

upvoted an article over 1 year ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

+1

Jul 18, 2024

•

61

upvoted a paper over 1 year ago

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions

Paper • 2403.16627 • Published Mar 25, 2024 • 22

upvoted a collection over 1 year ago

DBRX

DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27, 2024 • 96

upvoted 3 papers about 2 years ago

Orca 2: Teaching Small Language Models How to Reason

Paper • 2311.11045 • Published Nov 18, 2023 • 77

Efficient Few-Shot Learning Without Prompts

Paper • 2209.11055 • Published Sep 22, 2022 • 3

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

Paper • 2301.13688 • Published Jan 31, 2023 • 9