INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED BUT SOME MAY HAVE NO CONTENT It has had limited testing though, but seems relatively decent. Better than 8B at least. Findings: oproj and downproj can be stolen from Aethora-v2 so new 15B frankenmerges don’t seem to really need finetuning to «heal» the layers, though it has a big influence on the output so it’s slightly censored in one-shot. This is a merge of pre-trained language models created using mergekit. This model was merged using an iterative merging process. (Probably ~10 models got thrown away in the process.) The following models were included in the merge: grimjim/Llama-3-Instruct-abliteration-LoRA-8B UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS maldv/llama-3-fantasy-writer-8b …
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: v000000
Теги: llama, mergekit, merge, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 16
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
