Commit
•
21608c6
1
Parent(s):
e579085
Upload README.txt
Browse files- README.txt +14 -0
README.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- gozfarb/ShareGPT_Vicuna_unfiltered
|
| 4 |
+
---
|
| 5 |
+
# Convert tools
|
| 6 |
+
https://github.com/practicaldreamer/vicuna_to_alpaca
|
| 7 |
+
|
| 8 |
+
# Training on
|
| 9 |
+
https://github.com/oobabooga/text-generation-webui
|
| 10 |
+
|
| 11 |
+
ATM I'm using v4.3 of the dataset.
|
| 12 |
+
|
| 13 |
+
This LoRA is already pretty functional but far from finished training. ETA from the start 200 hours.
|
| 14 |
+
To use this LoRA please replace the config files to ones of Vicuna and I will have them here. Other than that use normal llama then replace the config files then load LoRA.
|