Text Classification
Transformers
Safetensors
decision-model
classification
julia
open-jev
head-finetune
low-resource
Instructions to use TypeSafeAI/Qyvos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TypeSafeAI/Qyvos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="TypeSafeAI/Qyvos")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TypeSafeAI/Qyvos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download provenance.json from TypeSafeAI/Qyvos: direct link, hf CLI and curl.
- Browser
- Download file 1.09 kB
-
https://huggingface.co/TypeSafeAI/Qyvos/resolve/main/provenance.json
- Command line
-
hf download hf://TypeSafeAI/Qyvos/provenance.json
-
curl -L -o provenance.json https://huggingface.co/TypeSafeAI/Qyvos/resolve/main/provenance.json
1.09 kB
| { | |
| "name": "Qyvos", | |
| "created_utc": "2026-09-30T21:28:03Z", | |
| "base_model": { | |
| "repo": "SupersonicLabs/Julia-1", | |
| "weights_sha256": "df853bf7fe424420011f3d0c47a05d7341aa9eefa7fb9f203ea4aada4ad95b72" | |
| }, | |
| "dataset": { | |
| "repo": "ZefanCai/Open-Jev", | |
| "config": "release-v2-redistributable", | |
| "shards": { | |
| "calibration-00000-of-00001.parquet": "74cf0064f68dcccbcedd4849d3b347f4c900bdd5329a78ec249fcdf24f89b554", | |
| "ood-00000-of-00001.parquet": "ba8cb3f95b9121aa73e4b997ac9c350e2ec4dddb972cb5c3086da911f0deb9ef", | |
| "test-00000-of-00001.parquet": "05edb50da60abb087328e353b201d83b745e01393b4a43b5320b90720a8132ff", | |
| "train-00000-of-00001.parquet": "a76be013b2986a97e4d61faad4fd5f0a6ddb934760d5dcf3161aaa118909b6bf", | |
| "validation-00000-of-00001.parquet": "5563764b2d92306e2bfdfd883edfee28a82acf36699f6533c0bd51978b784e59" | |
| } | |
| }, | |
| "backbone": "complete Julia-1 backbone retained bit-exact (encoder + act_head untouched)", | |
| "head": "fine-tuned on Open-Jev soft targets (choice/score/noul), 3,699,073 trainable params", | |
| "weights_dtype": "float32" | |
| } | |