taoki
/

phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF

Model card Files Files and versions Community

taoki commited on May 31

Commit

a7e5aab

•

1 Parent(s): 35317e5

Update README.md

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -13,4 +13,10 @@ language:
 - ja
 ---
-This repository contains models trained(QLoRA-SFT) model.

 - ja
 ---
+This repository contains a model trained (QLoRA-SFT) with the following data:
+- Base model: [Phi-3 mini 4k instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
+- Training data:
+  - sakusakumura/databricks-dolly-15k-ja-scored
+  - nu-dialogue/jmultiwoz
+  - kunishou/amenokaku-code-instruct
+  - HachiML/alpaca_jp_python