ewof
/

koishi-7b-qlora

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ewof commited on Dec 15, 2023

Commit

0e5ce15

•

1 Parent(s): fe1842a

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ datasets:
 ## Training
 [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
-on a 4x nvidia a40 gpu cluster.
 the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).
@@ -14,7 +14,7 @@ trained on koishi commit 6e675d1 for one epoch
 ## Base Model
-rank 8 lora tune of mistralai/Mistral-7B-v0.1 (merged)
 ## Prompting

 ## Training
 [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
+on a 6x nvidia a40 gpu cluster.
 the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).
 ## Base Model
+rank 16 lora tune of mistralai/Mistral-7B-v0.1 (all modules, merged)
 ## Prompting