Instructions to use emrevrg/AUBIN-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use emrevrg/AUBIN-12B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it") model = PeftModel.from_pretrained(base_model, "emrevrg/AUBIN-12B") - Notebooks
- Google Colab
- Kaggle
Download code/merge_dev.py from emrevrg/AUBIN-12B: direct link, hf CLI and curl.
- Browser
- Download file 552 Bytes
-
https://huggingface.co/emrevrg/AUBIN-12B/resolve/main/code/merge_dev.py
- Command line
-
hf download hf://emrevrg/AUBIN-12B/code/merge_dev.py
-
curl -L -o merge_dev.py https://huggingface.co/emrevrg/AUBIN-12B/resolve/main/code/merge_dev.py
552 Bytes
| """Ayrı koşuda ölçülen kev_dev'i (aynı adaptör) üye dosyasına ekler: python merge_dev.py üye.json dev.json çıktı.json""" | |
| import json, sys | |
| m, d, out = sys.argv[1:4] | |
| M = json.load(open(m, encoding="utf-8")); D = json.load(open(d, encoding="utf-8")) | |
| assert abs(M.get("runs_temperature", 1) - D.get("runs_temperature", 1)) < 1e-6, "sıcaklık farklı: aynı adaptör değil?" | |
| M["runs"]["kev_dev"] = D["runs"]["kev_dev"] | |
| json.dump(M, open(out, "w", encoding="utf-8")) | |
| print(out, M["runs_temperature"], D["runs"]["kev_dev"]["all"]["accuracy"]) | |