ausboss/llama2-13b-supercot-loras2

These are my 2nd round of Llama-2-13b SuperCOT Lora checkpoints trained using QLora on the SuperCOT Dataset with different parameters closer to the llama 1 supercot. — Model Architecture: Llama-2-13b — Training Algorithm: QLora — Dataset: SuperCOT Dataset — Datset type: alpaca — Training Parameters: See Here — Training Environment: Axolotl — sequencelen**: 4096 Special thanks to the creators of the datasets in SuperCOT. Additionally, thanks to Kaiokendev for curating the SuperCOT dataset. Thanks to the contributors of the Axolotl. The following bitsandbytes quantization config was used during training: — quantmethod: bitsandbytes — loadin8bit: False — loadin4bit: True — llmint8threshold: 6.0 — llmint8skipmodules: None — llmint8enablefp32cpuoffload: False — llmint8hasfp16weight: False — bnb4bitquanttype: nf4 — bnb4bitusedoublequant: True — bnb4bitcompute_dtype: bfloat16

Модальности:
Генерация текста

Задача: Генерация текста
Автор: ausboss
Теги: tensorboard, llama, endpoints_compatible, 4-bit, bitsandbytes
Лайков: 2  |  Загрузок: 17

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.