This LoRA model is based on the model from the paper Configurable Preference Tuning with Rubric-Guided Synthetic Data.
For code, see https://github.com/vicgalle/configurable-preference-tuning.
This LoRA model is based on the model from the paper Configurable Preference Tuning with Rubric-Guided Synthetic Data.
For code, see https://github.com/vicgalle/configurable-preference-tuning.
adapter_model.safetensors 228 MBtraining_args.bin 6.2 kB有文件？提交种子。
提交种子TheDrummer/Rocinante-12B-v1.1