Masterjp123
commited on
Commit
•
c0ecacd
1
Parent(s):
f17a801
Update README.md
Browse files
README.md
CHANGED
@@ -10,17 +10,47 @@ tags:
|
|
10 |
- merge
|
11 |
|
12 |
---
|
13 |
-
#
|
|
|
14 |
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Merge Details
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
### Merge Method
|
22 |
|
23 |
-
This model was merged using the [
|
24 |
|
25 |
### Models Merged
|
26 |
|
|
|
10 |
- merge
|
11 |
|
12 |
---
|
13 |
+
# Model
|
14 |
+
This is the Bf16 unquantized version of SnowyRP And the First Public Release of a Model in the SnowyRP series of models!
|
15 |
|
16 |
+
[BF16](https://huggingface.co/Masterjp123/SnowyRP-FinalV1-L2-13B)
|
17 |
+
|
18 |
+
[GPTQ](https://huggingface.co/Masterjp123/SnowyRP-FinalV1-L2-13B-GPTQ)
|
19 |
+
|
20 |
+
[GGUF](https://huggingface.co/Masterjp123/SnowyRP-FinalV1-L2-13B-GGUF)
|
21 |
+
|
22 |
+
Any Future Quantizations I am made aware of will be added.
|
23 |
|
24 |
## Merge Details
|
25 |
+
just originally made V2beta to be a test, But it seems like it is good, So I am quantizing it.
|
26 |
+
|
27 |
+
These models CAN and WILL produce X rated or harmful content, due to being heavily uncensored in a attempt to not limit or make the model worse.
|
28 |
+
|
29 |
+
This Model has a Very good knowledge base and understands anatomy decently, Plus this Model is VERY versitle and is great for General assistant work, RP and ERP, RPG RPs and much more.
|
30 |
+
|
31 |
+
## Model Use:
|
32 |
|
33 |
+
This model is very good... WITH THE RIGHT SETTINGS.
|
34 |
+
I personally use microstat mixed with dynamic temp with epsion cut off and eta cut off.
|
35 |
+
```
|
36 |
+
Optimal Settings (so far)
|
37 |
+
|
38 |
+
Microstat Mode: 2
|
39 |
+
tau: 2.95
|
40 |
+
eta: 0.05
|
41 |
+
|
42 |
+
Dynamic Temp
|
43 |
+
min: 0.25
|
44 |
+
max: 1.8
|
45 |
+
|
46 |
+
Cut offs
|
47 |
+
epsilon: 3
|
48 |
+
eta: 3
|
49 |
+
```
|
50 |
|
51 |
### Merge Method
|
52 |
|
53 |
+
This model was merged using the [ties](https://arxiv.org/abs/2306.01708) merge method using [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) as a base.
|
54 |
|
55 |
### Models Merged
|
56 |
|