SAS2Py — empero-ai/Qwythos-9B-Claude-Mythos-5-1M fine-tuned on SAS data
SAS→Python translation model fine-tuned on the SAS2Py dataset
(278 examples). Created by finetuning/finetune.py.
Hyperparameters
| Param | Value |
|---|---|
| LoRA r / alpha / dropout | 8 / 16 / 0.1 |
| Epochs | 3 |
| Learning rate | 0.0002 |
| Effective batch size | 1 x 16 = 16 |
| Max sequence length | 1024 |
| QLoRA (4-bit) | False |
| Trained | 20260715_181208 |
Prompt format
{instruction}
SAS:
{sas_code}
Python:
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("<this-repo-id>")
tokenizer = AutoTokenizer.from_pretrained("<this-repo-id>")