joe-hirst (Joe Hirst)

upvoted a collection 2 months ago

Gemma 3 Release

Collection

24 items • Updated 25 days ago • 359

upvoted 2 articles 3 months ago

Article

Remote VAEs for decoding with HF endpoints 🤗

Feb 24

• 39

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 477

upvoted a collection 4 months ago

DeepSeek-R1

Collection

8 items • Updated Jan 21 • 631

upvoted a paper 9 months ago

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

Paper • 2104.04045 • Published Apr 8, 2021 • 2

upvoted a collection 9 months ago

Training Datasets

Collection

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

upvoted 4 articles 9 months ago

Article

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

Jul 23, 2024

• 232

Article

Introducing TextImage Augmentation for Document Images

Aug 6, 2024

• 32

Article

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

May 24, 2023

• 145

Article

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

Aug 17, 2022

• 88

upvoted a collection 9 months ago

Llama 3.1 GPTQ, AWQ, and BNB Quants

Collection

Optimised Quants for high-throughput deployments! Compatible with Transformers, TGI & VLLM 🤗 • 9 items • Updated Sep 26, 2024 • 56

upvoted a collection 10 months ago

Gemma 2 2B Release

Collection

The 2.6B parameter version of Gemma 2. • 6 items • Updated Apr 3 • 79

upvoted an article 10 months ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Jul 18, 2024

• 58

upvoted a paper about 1 year ago

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

Paper • 2403.16627 • Published Mar 25, 2024 • 21

upvoted a collection about 1 year ago

DBRX

Collection

DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27, 2024 • 94

upvoted 3 papers over 1 year ago

Orca 2: Teaching Small Language Models How to Reason

Paper • 2311.11045 • Published Nov 18, 2023 • 75

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 • 8

Joe Hirst

AI & ML interests

Organizations

joe-hirst's activity

Gemma 3 Release

Remote VAEs for decoding with HF endpoints 🤗

Welcome to Inference Providers on the Hub 🔥

DeepSeek-R1

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

Training Datasets

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

Introducing TextImage Augmentation for Document Images

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

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

Llama 3.1 GPTQ, AWQ, and BNB Quants

Gemma 2 2B Release

TGI Multi-LoRA: Deploy Once, Serve 30 Models

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

DBRX

Orca 2: Teaching Small Language Models How to Reason

Efficient Few-Shot Learning Without Prompts

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