Instructions to use stojchet/kto2-sft1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stojchet/kto2-sft1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("stojchet/kto2-sft1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download params.json from stojchet/kto2-sft1: direct link, hf CLI and curl.
- Browser
- Download file 414 Bytes
-
https://huggingface.co/stojchet/kto2-sft1/resolve/main/params.json
- Command line
-
hf download hf://stojchet/kto2-sft1/params.json
-
curl -L -o params.json https://huggingface.co/stojchet/kto2-sft1/resolve/main/params.json
414 Bytes
| {"max_seq_length": 1000, "language": "kotlin", "dataset_size": "inf", "epochs": 3, "per_device_train_batch_size": 8, "gradient_accumulation_steps": 16, "weight_decay": 0.1, "learning_rate": 5e-05, "no_lora": true, "lora_r": 64, "lora_alpha": 16, "lora_dropout": 0.1, "dataset_name": "stojchet/base_prediction_dataset", "base_model": "deepseek-ai/deepseek-coder-1.3b-base", "dataset_ref_field": "whole_func_string"} |