Text Classification
Transformers
Safetensors
decision-model
classification
julia
open-jev
head-finetune
low-resource
Instructions to use SHSLab/Qyvos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SHSLab/Qyvos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SHSLab/Qyvos")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SHSLab/Qyvos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Qyvos v1: Julia-1 backbone (bit-exact) + Open-Jev head fine-tune (30k rows, low-RAM protocol)
31f7037 verified Download julia/probabilities.py from SHSLab/Qyvos: direct link, hf CLI and curl.
- Browser
- Download file 595 Bytes
-
https://huggingface.co/SHSLab/Qyvos/resolve/main/julia/probabilities.py
- Command line
-
hf download hf://SHSLab/Qyvos/julia/probabilities.py
-
curl -L -o probabilities.py https://huggingface.co/SHSLab/Qyvos/resolve/main/julia/probabilities.py
595 Bytes
| """Presentation rules for decision probabilities; logits and selection stay raw.""" | |
| def display_probabilities(probabilities): | |
| values = list(probabilities) | |
| if not values: | |
| return values | |
| winner = max(range(len(values)), key=values.__getitem__) | |
| if values[winner] > 0.95 and all( | |
| value < 0.045 for i, value in enumerate(values) if i != winner | |
| ): | |
| return [1.0 if i == winner else 0.0 for i in range(len(values))] | |
| visible = [value if value >= 0.01 else 0.0 for value in values] | |
| total = sum(visible) | |
| return [value / total for value in visible] | |