Casual-Autopsy commited on
Commit
7c9a263
·
verified ·
1 Parent(s): 84594c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -11
README.md CHANGED
@@ -1,34 +1,48 @@
1
  ---
2
  base_model:
3
- - NeverSleep/Noromaid-7B-0.4-DPO
4
  - kubernetes-bad/chargen-v2
5
- - NousResearch/Hermes-2-Pro-Mistral-7B
6
  - Weyaxi/Einstein-v4-7B
 
7
  library_name: transformers
8
  tags:
9
  - mergekit
10
  - merge
11
-
 
 
 
 
 
 
 
12
  ---
13
- # merge
14
 
15
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
16
 
17
  ## Merge Details
18
  ### Merge Method
19
 
20
- This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [kubernetes-bad/chargen-v2](https://huggingface.co/kubernetes-bad/chargen-v2) as a base.
21
 
22
  ### Models Merged
23
 
24
- The following models were included in the merge:
25
- * [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)
26
- * [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
27
- * [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
 
 
 
 
 
28
 
29
  ### Configuration
30
 
31
- The following YAML configuration was used to produce this model:
 
32
 
33
  ```yaml
34
  models:
@@ -55,3 +69,5 @@ parameters:
55
  dtype: float32
56
  out_dtype: bfloat16
57
  ```
 
 
 
1
  ---
2
  base_model:
 
3
  - kubernetes-bad/chargen-v2
4
+ - NeverSleep/Noromaid-7B-0.4-DPO
5
  - Weyaxi/Einstein-v4-7B
6
+ - NousResearch/Hermes-2-Pro-Mistral-7B
7
  library_name: transformers
8
  tags:
9
  - mergekit
10
  - merge
11
+ - character_creation
12
+ - world-building
13
+ - lore_writing
14
+ - not-for-all-audiences
15
+ - nsfw
16
+ language:
17
+ - en
18
+ pipeline_tag: text-generation
19
  ---
20
+ # WorldGen-v1.1
21
 
22
+ WorldGen is a merge designed to enhance the capabilities of the character creation model, CharGen. While CharGen is great for creating characters, even to this day given its age, but it struggles at effectively making Lorebook/WorldInfo entries.</br>
23
+ However, by merging it with an RP LLM and two LLMs that contain some scientific data and are good at instruction following I was able to make it more reliable at world-building.
24
 
25
  ## Merge Details
26
  ### Merge Method
27
 
28
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [kubernetes-bad/chargen-v2](https://huggingface.co/kubernetes-bad/chargen-v2) as a base, created using [mergekit](https://github.com/cg123/mergekit).
29
 
30
  ### Models Merged
31
 
32
+ <details><summary>The following models were included in the merge:</summary>
33
+ <b>Merge Tree:</b>
34
+
35
+ [kubernetes-bad/chargen-v2](https://huggingface.co/kubernetes-bad/chargen-v2)</br>
36
+ &nbsp;&nbsp;&nbsp;&nbsp;⌊ [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)</br>
37
+ &nbsp;&nbsp;&nbsp;&nbsp;⌊ [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)</br>
38
+ &nbsp;&nbsp;&nbsp;&nbsp;⌊ [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
39
+
40
+ </details>
41
 
42
  ### Configuration
43
 
44
+ <details><summary>The following YAML configuration was used to produce this model:</summary>
45
+ <b>Merge Recipe:</b>
46
 
47
  ```yaml
48
  models:
 
69
  dtype: float32
70
  out_dtype: bfloat16
71
  ```
72
+
73
+ </details>