Skip to content

Latest commit

 

History

History
22 lines (16 loc) · 2.23 KB

README.md

File metadata and controls

22 lines (16 loc) · 2.23 KB

BLOOM - Quantized Inference + QLoRA Finetuning on T4

Inference

Model Notebook Links
BLOOM 7B1/4bit bloom_7b1_4bit_inference.ipynb Open In Colab Open in SageMaker Studio Lab
BLOOM 3B/4bit bloom_3b_4bit_inference.ipynb Open In Colab Open in SageMaker Studio Lab
BLOOM 1B7 bloom_1b7_inference.ipynb Open In Colab Open in SageMaker Studio Lab

Finetuning

Model Dataset Notebook Links
BLOOM 3B/4bit Dolly bloom_3b_4bit_qlora_finetuning_with_dolly.ipynb Open In Colab Open in SageMaker Studio Lab

Task List

  • Finetuning with Tim Dettmers OASST
  • Finetuning with Nvidia HelpSteer
  • DeepSpeed
  • GPTQ