Working models - a Pretrain-FBK-NLP Collection

Pretrain-FBK-NLP 's Collections

FT models Italian med tasks

Working models

updated Sep 8

Pretrain-FBK-NLP/Llama-3.2-1B_AllDataSourcesClinical_0.0002_constant_512_paper

Text Generation • 1B • Updated May 7 • 8
Pretrain-FBK-NLP/Llama-3.2-1B_AllDataSourcesClinical_0.0002_cosine_512_paper

Text Generation • 1B • Updated May 7 • 10
Pretrain-FBK-NLP/mt5-large_AllDataSourcesClinical_0.0002_constant_512_paper

Updated May 8
Pretrain-FBK-NLP/Llama-3.2-1B_AllDataSourcesClinical_0.0002_constant_1024_paper

Text Generation • 1B • Updated May 13 • 11
Pretrain-FBK-NLP/Llama-3.2-1B_AllDataSourcesClinical_0.0002_cosine_1024_paper

Text Generation • 1B • Updated May 12 • 9
Pretrain-FBK-NLP/mt5-large_AllDataSourcesClinical_0.0002_constant_1024_paper

1B • Updated May 26 • 9
Pretrain-FBK-NLP/mt5-large_AllDataSourcesClinical_0.0002_cosine_1024_paper

1B • Updated May 27 • 9
Pretrain-FBK-NLP/Llama-3.2-1B-Instruct_AllDataSourcesClinical_0.0002_cosine_1024_paper

Text Generation • 1B • Updated Jun 10 • 13
Pretrain-FBK-NLP/gemma-3-1b-pt_AllDataSourcesClinical_0.0002_cosine_1024_paper

Text Generation • 1.0B • Updated Aug 27 • 12
Pretrain-FBK-NLP/gemma-3-1b-it_AllDataSourcesClinical_0.0002_cosine_1024_paper

Text Generation • 1.0B • Updated Jun 13 • 9
Pretrain-FBK-NLP/Qwen3-1.7B_AllDataSourcesClinical_0.0002_cosine_1024_paper

Text Generation • 2B • Updated Sep 5 • 5