Text Classification
PEFT
Safetensors
English
decision-model
calibration
lora
multiple-choice
typesafe
prototype
Eval Results (legacy)
Instructions to use Terom/kev-0.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Terom/kev-0.5b with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen2.5-0.5B") model = PeftModel.from_pretrained(base_model, "Terom/kev-0.5b") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Terom/kev-0.5b: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/Terom/kev-0.5b/resolve/main/tokenizer.json
- Command line
-
hf download hf://Terom/kev-0.5b/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Terom/kev-0.5b/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 4bd2f092eeec244c0448f13e31edd4b25e625568713e4155993a3dea90c7437a
- Size of remote file:
- 11.4 MB
- SHA256:
- 9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.