Refusal in Language Models Is Mediated by a Single Direction Paper โข 2406.11717 โข Published 12 days ago โข 1
abliterated-v3 Collection Latest gen of the abliterated models I've produced โข 17 items โข Updated 26 days ago โข 69
view article Article โ๏ธ ๐ฅ Building High-Quality Datasets with distilabel and Prometheus 2 By burtenshaw โข 26 days ago โข 21
view article Article Training and Finetuning Embedding Models with Sentence Transformers v3 May 28 โข 104
Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA Paper โข 2405.07101 โข Published May 11 โข 1
view article Article Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent Apr 22 โข 75
๐ฎ๐น Italian NLP Resources Collection Collection of models, datasets and demos relevant to Italian NLP ๐ฎ๐น โข 188 items โข Updated 7 days ago โข 18
About ORPO Collection Contains some information and experiments fine-tuning LLMs using ๐ค `trl.ORPOTrainer` โข 8 items โข Updated May 7 โข 5
Model Merging Collection 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! โข 30 items โข Updated 17 days ago โข 189
Flan-T5 release Collection The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling โข 7 items โข Updated 2 days ago โข 14