zhouliang
commited on
Commit
•
cc31432
1
Parent(s):
92c0ed7
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,9 @@ tags:
|
|
| 12 |
|
| 13 |
**Deepsex-34b**
|
| 14 |
|
|
|
|
|
|
|
|
|
|
| 15 |
Here are the steps to make this model:
|
| 16 |
1. I first collected a total collection of about 4GB of various light novels, and used BERT to perform two rounds of similarity deduplication on the novels with similar plots in the data set. In addition, a portion of nsfw novels are mixed in to improve the NSFW capabilities of the model.
|
| 17 |
2. Then use the YI-34B-base as the base of the model, use the setting of r=64 alpha=128 and use qlora to fine-tune 3 epochs for continuous pre-training.
|
|
|
|
| 12 |
|
| 13 |
**Deepsex-34b**
|
| 14 |
|
| 15 |
+
gguf:https://huggingface.co/zzlgreat/deepsex-34b-gguf
|
| 16 |
+
exl2:https://huggingface.co/waldie/deepsex-34b-4bpw-h6-exl2
|
| 17 |
+
|
| 18 |
Here are the steps to make this model:
|
| 19 |
1. I first collected a total collection of about 4GB of various light novels, and used BERT to perform two rounds of similarity deduplication on the novels with similar plots in the data set. In addition, a portion of nsfw novels are mixed in to improve the NSFW capabilities of the model.
|
| 20 |
2. Then use the YI-34B-base as the base of the model, use the setting of r=64 alpha=128 and use qlora to fine-tune 3 epochs for continuous pre-training.
|