athirdpath
commited on
Commit
•
2977607
1
Parent(s):
48d1228
Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,8 @@ pipeline_tag: text-generation
|
|
13 |
|
14 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
15 |
|
|
|
|
|
16 |
# qlora
|
17 |
|
18 |
This model is a fine-tuned version of [athirdpath/BigMistral-11b](https://huggingface.co/athirdpath/BigMistral-11b) on the athirdpath/Merge_Glue dataset.
|
|
|
13 |
|
14 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
15 |
|
16 |
+
<p align="center"><font size="5"> <b>MAJOR regret: Should have not targeted Q, V, K, O; as those are less impactful for "healing" but more impactful on performance otherwise. </b> </font></p>
|
17 |
+
|
18 |
# qlora
|
19 |
|
20 |
This model is a fine-tuned version of [athirdpath/BigMistral-11b](https://huggingface.co/athirdpath/BigMistral-11b) on the athirdpath/Merge_Glue dataset.
|