anakin87/gemma-2-9b-neogenesis-ita

Text Generation • Updated 29 days ago • 3.08k • 8

Note 9B model: DPO starting from SauerkrautLM-gemma-2-9b-it

anakin87/gemma-2-2b-neogenesis-ita

Text Generation • Updated 29 days ago • 2.76k • 6

Note Final 2B model: SFT + DPO starting from gemma-2-2b-it

Note Try the 9B model!

Note Try the 2B model!

anakin87/gemma-2-2b-ita-sft

Text Generation • Updated Jan 11 • 14

Note Intermediate 2B model: SFT starting from gemma-2-2b-it

mradermacher/gemma-2-2b-neogenesis-ita-GGUF

Updated about 1 month ago • 254 • 2

Note Static GGUF quants

mradermacher/gemma-2-2b-neogenesis-ita-i1-GGUF

Updated about 1 month ago • 410 • 2

Note Weighted/imatrix quants

Note Initial dataset to translate

Note Italian SFT dataset, obtained from FineTome-single-turn-dedup with LLM-aided translation

Note Italian Preference dataset, obtained by reranking efederici/evol-dpo-ita

Note On-policy data generated with gemma-2-2b-ita-sft and evaluated with Llama-3.3-70B-Instruct to do DPO