metadata
library_name: peft
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.4.0
Citation and attribution
This model release is maintained by Gökay Aydoğan. If you reference this repository in academic work, please cite it as follows and also cite the upstream models, datasets, or projects it builds upon.
@software{aydogan2024phi2_desctoprompt,
author = {Aydoğan, Gökay},
title = {{phi2_desctoprompt}},
year = {2024},
publisher = {Hugging Face},
url = {https://huggingface.co/gokaygokay/phi2_desctoprompt},
note = {Model repository; cite the base model and upstream datasets as required.}
}