Stefano Fiorucci's picture

Stefano Fiorucci

anakin87

·

https://stefano-fiorucci.netlify.app

AI & ML interests

Contributing to Haystack, the LLM Framework 🏗️. NLP / LLMs.

Organizations

anakin87's activity

upvoted an article 5 days ago

Article

Mixedbread 🤝 deepset: Announcing our New German/English Embedding Model

By

•

5 days ago

• 13

upvoted an article 6 days ago

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

By

•

Jun 4

• 65

upvoted a paper 30 days ago

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17 • 1

upvoted a collection about 1 month ago

abliterated-v3

Latest gen of the abliterated models I've produced • 17 items • Updated Jun 3 • 75

upvoted 3 articles about 2 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 239

Article

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

By

•

Jun 3

• 21

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 124

upvoted a paper 2 months ago

Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA

Paper • 2405.07101 • Published May 11 • 1

upvoted an article 3 months ago

Article

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Apr 22

• 76

upvoted 2 collections 4 months ago

🇮🇹 Italian NLP Resources

Collection of models, datasets and demos relevant to Italian NLP 🇮🇹 • 196 items • Updated about 14 hours ago • 18

About ORPO

Contains some information and experiments fine-tuning LLMs using 🤗 `trl.ORPOTrainer` • 8 items • Updated May 7 • 5

upvoted 3 collections 6 months ago

Model Merging

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12 • 196

Italian NER

5 items • Updated Dec 11, 2023 • 1

Italian Sentence Transformers

11 items • Updated Feb 23 • 6

upvoted a paper 9 months ago

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 120

upvoted a collection 10 months ago

Flan-T5 release

The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling • 7 items • Updated 26 days ago • 16