Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,10 @@ language:
|
|
| 8 |
|
| 9 |
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
Qlora trained for 5 epochs on 6400 rows of q&a from around 1000 pages from wikipedia + around 100 of python questions and examples from
|
| 12 |
eph1/Alpaca-Lora-GPT4-Swedish-Refined (because I had spent so much time cleaning them and didn't want to throw them away). Also a couple of hundred rows of manually
|
| 13 |
gathered examples and some generated using chat-gpt.
|
|
|
|
| 8 |
|
| 9 |
|
| 10 |
|
| 11 |
+
Update 240103: I'm currently retraining on Colab with a larger dataset but I'm running into issues due to reaching the limits of the V100. A100 don't seem to be available.
|
| 12 |
+
May be some time before the new version is done.
|
| 13 |
+
|
| 14 |
+
|
| 15 |
Qlora trained for 5 epochs on 6400 rows of q&a from around 1000 pages from wikipedia + around 100 of python questions and examples from
|
| 16 |
eph1/Alpaca-Lora-GPT4-Swedish-Refined (because I had spent so much time cleaning them and didn't want to throw them away). Also a couple of hundred rows of manually
|
| 17 |
gathered examples and some generated using chat-gpt.
|