The objective of this model is to serve as a fully open source new base model with 14.3 billion parameters. It has been enhanced with a LoRa adapter attached to all 62 layers of the merged model. The model is capable of generating outputs and responding accurately to inputs. However, it tends to over-respond with unasked questions when asked to process more than 512 tokens, which is its training limit using QLoRa. With full fine-tuning, this model has the potential to deliver excellent performance. Qlora adapter was trained on a modified dataset of airoboros-m-7b-3.1.2, using SFT. In the Alpaca Format. The model was created by merging two models: Dolphin and Zephyr, along with Meta-math7b and Speechless code, to form a single model. The layers of these two models were stacked on top of each other to create this model. Initially, the output from the model was pure jargon. To rectify this, a LoRa adapter was trained and merged across all layers. — LoRa Adapter Merging (https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930) — Model Merging (MergeKit) (https://github.com/cg123/mergekit) — Dolphin2.1-mistral-7b by Eric Hartford…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Vezora
Теги: mistral, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 51
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.