Instructions to use codegood/MistralLite_SCQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use codegood/MistralLite_SCQA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("amazon/MistralLite") model = PeftModel.from_pretrained(base_model, "codegood/MistralLite_SCQA") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from codegood/MistralLite_SCQA: direct link, hf CLI and curl.
- Browser
- Download file 369 MB
-
https://huggingface.co/codegood/MistralLite_SCQA/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://codegood/MistralLite_SCQA/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/codegood/MistralLite_SCQA/resolve/main/adapter_model.safetensors
369 MB
- Xet hash:
- 07434edd9ac8ce462756003982911ce58fae9bffb744e91ac1ba93c515c007f4
- Size of remote file:
- 369 MB
- SHA256:
- ce3568d79313a585b806cf7e0cbeda8bba4ac45c07106c97b8ef7bfb965ceb7b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.