Instructions to use cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Phi-3-mini-4k-instruct") model = PeftModel.from_pretrained(base_model, "cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.model from cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7: direct link, hf CLI and curl.
- Browser
- Download file 500 kB
-
https://huggingface.co/cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7/resolve/main/tokenizer.model
- Command line
-
hf download hf://cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7/resolve/main/tokenizer.model
500 kB
- Xet hash:
- 91bf184ab12793d0754344f9095332759432e666320cc6c07f637af50e36db6f
- Size of remote file:
- 500 kB
- SHA256:
- 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.