This model is a fine-tuned version of Photolens/llama-2-7b-langchain-chat on the OneOS dataset. json {«action»: «Final Answer», «action_input»: «I am Assistant, a sentient artificial intelligence. I am a machine learning model that has been trained on a large dataset of text to understand and generate human-like language. I am designed to be helpful and informative, and I am here to assist you with any questions or tasks you may have.»} The following hyperparameters were used during training: — learningrate: 1.41e-05 — trainbatchsize: 2 — evalbatchsize: 8 — seed: 42 — gradientaccumulationsteps: 2 — totaltrainbatchsize: 4 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: linear — num_epochs: 1 Model is able to mostly answer to complexe queries given its output is p — Transformers 4.33.2 — Pytorch 2.0.1+cu117 — Datasets 2.14.5 — Tokenizers 0.13.3 The below are links that lead to conversation logs between Assistant using this model and me. https://gist.github.com/wasertech/342cd167ba78060336b3328e9eea0eca…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: wasertech
Теги: llama, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 24
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.