Zero-Shot Classification
PEFT
Safetensors
English
lev
system-one
decision-model
calibrated-decisions
classification
routing
moderation
lora
Instructions to use helmo/lev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use helmo/lev with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "helmo/lev") - Notebooks
- Google Colab
- Kaggle
Download assets/accuracy-per-parameter.png from helmo/lev: direct link, hf CLI and curl.
- Browser
- Download file 103 kB
-
https://huggingface.co/helmo/lev/resolve/main/assets/accuracy-per-parameter.png
- Command line
-
hf download hf://helmo/lev/assets/accuracy-per-parameter.png
-
curl -L -o accuracy-per-parameter.png https://huggingface.co/helmo/lev/resolve/main/assets/accuracy-per-parameter.png
103 kB

- Xet hash:
- 5b6dc2a303b1947b6ad85c97e3e0db50bcf3a234fd3f28a9f79e6ed698aadf99
- Size of remote file:
- 103 kB
- SHA256:
- ed5465d6df019c81594c05434b7b1e890f5f8e696562dbc97d2b91f92f504022
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.