Instructions to use jason1966/CoPaw-Flash-9B-DataAnalyst-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jason1966/CoPaw-Flash-9B-DataAnalyst-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/shadeform/CoPaw-Flash-9B") model = PeftModel.from_pretrained(base_model, "jason1966/CoPaw-Flash-9B-DataAnalyst-LoRA") - Notebooks
- Google Colab
- Kaggle
How to run this with 8-bit quantized (or lower)
#1
by lexat - opened
I have only 12GB of VRAM. Is it possible to run it?
Yes! For 8-bit quantization: It works fine for short texts, but long contexts will likely cause an OOM (Out of Memory) error.
Can you please provide command or instruction how to run it with 12GB of VRAM?