Update README.md
Browse files
README.md
CHANGED
@@ -10,15 +10,17 @@ tags:
|
|
10 |
- roleplay
|
11 |
---
|
12 |
|
13 |
-
Calibration dataset
|
|
|
|
|
14 |
|
15 |
**Deepsex-34b**
|
16 |
|
17 |
-
gguf:https://huggingface.co/zzlgreat/deepsex-34b-gguf
|
18 |
|
19 |
-
exl2:https://huggingface.co/waldie/deepsex-34b-4bpw-h6-exl2
|
20 |
|
21 |
-
exl2:https://huggingface.co/Redwood0/deepsex-34b-4bpw-h8-exl2
|
22 |
|
23 |
Here are the steps to make this model:
|
24 |
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.
|
|
|
10 |
- roleplay
|
11 |
---
|
12 |
|
13 |
+
**Calibration dataset**: VMware Open Instruct, 4096 tokens per sample
|
14 |
+
|
15 |
+
|
16 |
|
17 |
**Deepsex-34b**
|
18 |
|
19 |
+
gguf: https://huggingface.co/zzlgreat/deepsex-34b-gguf
|
20 |
|
21 |
+
exl2: https://huggingface.co/waldie/deepsex-34b-4bpw-h6-exl2
|
22 |
|
23 |
+
exl2: https://huggingface.co/Redwood0/deepsex-34b-4bpw-h8-exl2
|
24 |
|
25 |
Here are the steps to make this model:
|
26 |
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.
|