Afonso Marques's picture

Afonso Marques

marquesafonso

·

marquesafonso

AI & ML interests

None yet

Recent Activity

upvoted an article 6 days ago

Agentic RAG Stack (3/5) - Generate responses using a SmolLM

upvoted an article 7 days ago

Agentic RAG Stack (1/5) - Index and retrieve documents for vector search using Sentence Transformers and DuckDB

upvoted an article 7 days ago

Agentic RAG Stack (2/5) - Augment retrieval results by reranking using Sentence Transformers

View all activity

Organizations

None yet

marquesafonso's activity

upvoted an article 6 days ago

Article

Agentic RAG Stack (3/5) - Generate responses using a SmolLM

By

•

6 days ago

• 6

upvoted 2 articles 7 days ago

Article

Agentic RAG Stack (1/5) - Index and retrieve documents for vector search using Sentence Transformers and DuckDB

By

•

16 days ago

• 16

Article

Agentic RAG Stack (2/5) - Augment retrieval results by reranking using Sentence Transformers

By

•

7 days ago

• 7

upvoted an article 9 days ago

Article

Replicating DeepSeek R1 for Information Extraction

By

•

12 days ago

• 30

upvoted an article 20 days ago

Article

Mastering Long Contexts in LLMs with KVPress

By

and 1 other •

20 days ago

• 62

upvoted an article 27 days ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

28 days ago

• 142

upvoted an article 30 days ago

Article

Use Models from the Hugging Face Hub in LM Studio

By

•

Nov 28, 2024

• 138

upvoted 2 papers about 1 month ago

GLiREL -- Generalist Model for Zero-Shot Relation Extraction

Paper • 2501.03172 • Published Jan 6 • 1

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

Paper • 2408.04303 • Published Aug 8, 2024 • 18

upvoted a collection about 1 month ago

Granite 3.1 Language Models

A series of language models with 128K context length trained by IBM licensed under Apache 2.0 license. • 8 items • Updated Dec 18, 2024 • 53

upvoted an article about 2 months ago

Article

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

By

•

Jul 9, 2024

• 42

upvoted 4 collections 2 months ago

Positions Datasets

Datasets where each row is a chess position • 4 items • Updated Jan 9 • 6

Common Models

The first generation of models pretrained on Common Corpus. • 5 items • Updated Dec 5, 2024 • 29

EuroLLM

4 items • Updated Dec 2, 2024 • 27

Tucano

Tucano is a series of decoder-transformers based on the Llama 2 architecture, natively pre-trained in Portuguese. • 17 items • Updated Nov 13, 2024 • 2

upvoted 2 collections 3 months ago

NuExtract-1.5

4 items • Updated Nov 15, 2024 • 4

Common Corpus

Largest multilingual pretraining data. • 1 item • Updated Nov 13, 2024 • 9

upvoted a paper 4 months ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1, 2024 • 145

upvoted a collection 5 months ago

LLM2Encoder

Collection of initial models and models that use converted decoders to encoders as backbones • 11 items • Updated Sep 10, 2024 • 6

upvoted a collection 6 months ago

GLiNER bi-encoders

Bi-encoder and poly-encoder architectures of GLiNER • 5 items • Updated Sep 10, 2024 • 13