This is a merge of pre-trained language models created using mergekit. Basically. How many fucking models can you merge into 1 and still stay coherent, 24 is the answer (Though i might do a bigger one) FP8: https://huggingface.co/SanXM1/Driftwood-12b-FP8/ EXL2: https://huggingface.co/NewEden/Delta-Vector_driftwood-exl2 This model was merged using the Model Stock merge method using IntervitensInc/Mistral-Nemo-Base-2407-chatml as a base. The following models were included in the merge: nbeerbower/Lyra4-Gutenberg2-12B Nitral-AI/Captain-ErisViolet-GRPO-v0.420 nbeerbower/Mistral-Nemo-Prism-12B nbeerbower/mistral-nemo-bophades-12B NeverSleep/Lumimaid-v0.2-12B Nitral-AI/WayfarerErisNoctis-12B Undi95/LocalC-12B-e2.0 PygmalionAI/Pygmalion-3-12B Delta-Vector/Ohashi-NeMo-12B Delta-Vector/Francois-Huali-12B anthracite-org/magnum-v4-12b nbeerbower/mistral-nemo-gutenberg-12B-v4 LatitudeGames/Wayfarer-12B al
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: SanXM1
Теги: mistral, mergekit, merge, conversational, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 14
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
