Instructions to use emilyseong/pmc_attnpool_gpu4_cumsum_spi2e-5_proj2e-5_llm2e-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use emilyseong/pmc_attnpool_gpu4_cumsum_spi2e-5_proj2e-5_llm2e-5 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/llava-med-v1.5-mistral-7b") model = PeftModel.from_pretrained(base_model, "emilyseong/pmc_attnpool_gpu4_cumsum_spi2e-5_proj2e-5_llm2e-5") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 0406197364a3e1e5947d0f3f8ee3eb4ee342f3e2b00229c4fcc13dcc17ab8fcc
- Size of remote file:
- 671 MB
- SHA256:
- 0bbc290ac6bac5e52eeb1593164611ee8caf9d05d7571df39d3480048ec82aa2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.