Davide Mazzaccara's picture

3 1

Davide Mazzaccara

mazzaqq

·

AI & ML interests

Computational Linguistics, NLP

Recent Activity

updated a model 15 minutes ago

clembench-playpen/meta-llama-3.1_DPO_1neg_Aborted_best_models_END_07

published a model about 3 hours ago

clembench-playpen/meta-llama-3.1_DPO_1neg_Aborted_best_models_END_07

updated a collection about 9 hours ago

SFT Final Models Merged

View all activity

Organizations

models 24

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_KTO_wordle_wordlewithclue_aborted

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_KTO_wordle_wordlewithclue

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_allneg_same_family_model

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_6neg_NEW

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_3neg_NEW

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_2neg_NEW

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_1neg_NEW

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct-dpo_3neg_REV

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct-dpo_1neg_REV

mazzaqq/meta-llama-Meta-Llama-3.1-8B-Instruct-dpo_2neg_REV

datasets 21

mazzaqq/binary_dataset_wordle_wordlewithclue_aborted

Viewer • Updated Jan 29 • 5.67k • 47

mazzaqq/playpen_dpo_6neg

Viewer • Updated Jan 23 • 12.2k • 51

mazzaqq/playpen_dpo_2neg

Viewer • Updated Jan 23 • 5.01k • 62

mazzaqq/playpen_dpo_1neg

Viewer • Updated Jan 23 • 2.61k • 60

mazzaqq/playpen_dpo_3neg

Viewer • Updated Jan 23 • 7.25k • 54

mazzaqq/kto_dataset_try_no_chat

Viewer • Updated Jan 11 • 6.06k • 49

mazzaqq/kto_dataset_small

Viewer • Updated Jan 10 • 5.41k • 53

mazzaqq/playpen_dpo_6neg_per_pos

Viewer • Updated Dec 20, 2024 • 16.2k • 47

mazzaqq/playpen_dpo_3neg_per_pos

Viewer • Updated Dec 20, 2024 • 8.76k • 52

mazzaqq/playpen_dpo_2neg_per_pos

Viewer • Updated Dec 20, 2024 • 5.93k • 42