Edit model card

This repository contains a model trained (QLoRA-SFT) with the following data:

  • Base model: Phi-3 mini 4k instruct
  • Training data:
    • sakusakumura/databricks-dolly-15k-ja-scored
    • nu-dialogue/jmultiwoz
    • kunishou/amenokaku-code-instruct
    • HachiML/alpaca_jp_python
Downloads last month
3
GGUF
Model size
3.82B params
Architecture
phi3

4-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for taoki/phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF

Quantized
(98)
this model

Datasets used to train taoki/phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF