Guille Pérez-Torró

guishe

AI & ML interests

Information Retrieval, Few-Shot Learning, Named Entity Recognition, Named Entity Disambiguation, Semantic Search, Aspect-based Sentiment Analysis

Recent Activity

upvoted a collection about 19 hours ago

Unsloth 4-bit Dynamic Quants

updated a collection 3 days ago

Reasoning LLMs

liked a model 4 days ago

unsloth/Llama-3.1-Storm-8B-bnb-4bit

View all activity

Organizations

None yet

guishe's activity

upvoted a collection about 19 hours ago

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 23 items • Updated 2 days ago • 61

upvoted a paper 17 days ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20, 2024 • 90

upvoted a collection 23 days ago

4bit Instruct Models

Collection

18 items • Updated 2 days ago • 28

upvoted an article 23 days ago

Article

Tutorial: Quantizing Llama 3+ Models for Efficient Deployment

•

Dec 15, 2024

• 4

upvoted a paper 25 days ago

Matryoshka Quantization

Paper • 2502.06786 • Published Feb 10 • 29

upvoted 2 articles about 1 month ago

Article

Unleashing the Power of Unsloth and QLora:Redefining Language Model Fine-Tuning

•

Jan 19, 2024

• 13

Article

Selene 1 Mini: the best small language model-as-a-judge

and 10 others •

Jan 29

• 12

upvoted an article about 2 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

• 159

upvoted a paper 3 months ago

GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks

Paper • 2406.12925 • Published Jun 14, 2024 • 24

upvoted a collection 4 months ago

SmolLM2

Collection

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated 22 days ago • 246

upvoted a paper 4 months ago

HelpSteer2-Preference: Complementing Ratings with Preferences

Paper • 2410.01257 • Published Oct 2, 2024 • 23

upvoted an article 5 months ago

Article

How to build a custom text classifier without days of human labeling

and 4 others •

Oct 17, 2024

• 55

upvoted 3 articles 6 months ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

• 86

Article

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

•

Jul 22, 2024

• 5

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22, 2024

• 77

upvoted 2 articles 7 months ago

Article

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

Jul 23, 2024

• 230

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

•

Jul 29, 2024

• 293

upvoted 2 collections 7 months ago

Zeroshot Classifiers

Collection

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 12 items • Updated Jan 6 • 128

ReLiK: Retrieve, Read and LinK

Collection

A blazing fast and lightweight Information Extraction model for Entity Linking and Relation Extraction. • 20 items • Updated Dec 4, 2024 • 24

upvoted a paper 8 months ago

Nomic Embed: Training a Reproducible Long Context Text Embedder

Paper • 2402.01613 • Published Feb 2, 2024 • 15