This model is a fine-tuned version of chargoddard/internlm2-20b-llama on the None dataset. The following bitsandbytes quantization config was used during training: — quantmethod: bitsandbytes — loadin8bit: True — loadin4bit: False — llmint8threshold: 6.0 — llmint8skipmodules: None — llmint8enablefp32cpuoffload: False — llmint8hasfp16weight: False — bnb4bitquanttype: fp4 — bnb4bitusedoublequant: False — bnb4bitcompute_dtype: float32 The following hyperparameters were used during training: — learningrate: 0.0002 — trainbatchsize: 2 — evalbatchsize: 2 — seed: 42 — gra
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Weyaxi
Теги: llama, axolotl, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 15
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.