Text Classification
Transformers
qwen3_5_text
typed-decisions
decision-model
system-one
jev-compatible
custom-code
Instructions to use GyrTechnology/saif-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GyrTechnology/saif-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GyrTechnology/saif-4b")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GyrTechnology/saif-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download export.json from GyrTechnology/saif-4b: direct link, hf CLI and curl.
- Browser
- Download file 520 Bytes
-
https://huggingface.co/GyrTechnology/saif-4b/resolve/main/export.json
- Command line
-
hf download hf://GyrTechnology/saif-4b/export.json
-
curl -L -o export.json https://huggingface.co/GyrTechnology/saif-4b/resolve/main/export.json
520 Bytes
| { | |
| "checkpoint": "/home/sultan/saif/checkpoints/d1/continuous/saif4-core/cooldown-r0/final", | |
| "weights_sha256": "b5a6cb723ff7b0d5f5d8bc39c8dcfbecb7726fd1a9bb6124bf81ed769841bd10", | |
| "temperatures": "raw1.0 (refit recorded, not applied)", | |
| "parity": { | |
| "records": 30, | |
| "max_delta": 0.0, | |
| "mean_delta": 0.0, | |
| "argmax_agreement": 1.0, | |
| "thresholds": "v3 export: max<=0.02, mean<=0.002, all argmax agree" | |
| }, | |
| "serving_code_from": "/home/sultan/saif/runs/d1/perfect/saif-v3-0p8b-final-di-fast/serving" | |
| } | |