Using □ PEFT LoRA for tuning bigscience/T0_3B model (3 Billion parameters) on consumer hardware with 11GB of RAM, such as Nvidia GeForce RTX 2080 Ti, Nvidia GeForce RTX 3080, etc using □ Accelerate's DeepSpeed integration: peft_lora_seq2seq_accelerate_ds_zero3_offload.py. These are a few of the most interesting ones: We explore many interesting use cases here.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |