Instructions to use codegood/Mistral_SC_QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use codegood/Mistral_SC_QA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("alexsherstinsky/Mistral-7B-v0.1-sharded") model = PeftModel.from_pretrained(base_model, "codegood/Mistral_SC_QA") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from codegood/Mistral_SC_QA: direct link, hf CLI and curl.
- Browser
- Download file 336 MB
-
https://huggingface.co/codegood/Mistral_SC_QA/resolve/main/adapter_model.bin
- Command line
-
hf download hf://codegood/Mistral_SC_QA/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/codegood/Mistral_SC_QA/resolve/main/adapter_model.bin
336 MB
- Xet hash:
- 1f3bf512b66708f8ab36f97c57c104204cbc8e337e42413f2891a4609ccfcd96
- Size of remote file:
- 336 MB
- SHA256:
- 48c07f2cc2c99676fa4e35d9a4c2d46768a049cd76f53834aaca731d07171fb2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.