KaraKaraWitch commited on
Commit
0882ae3
·
verified ·
1 Parent(s): 1702829

Retain older readme. It's the same but with a fixed o_proj. So no need to update readme.

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  base_model:
3
- - Qwen/Qwen3-30B-A3B
4
  - Qwen/Qwen3-30B-A3B-Base
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
@@ -10,6 +10,11 @@ tags:
10
  ---
11
  # CavesOfQwen
12
 
 
 
 
 
 
13
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
 
15
  ## Merge Details
@@ -42,4 +47,4 @@ base_model: Qwen/Qwen3-30B-A3B
42
  parameters:
43
  normalize: true
44
  dtype: bfloat16
45
- ```
 
1
  ---
2
  base_model:
 
3
  - Qwen/Qwen3-30B-A3B-Base
4
+ - Qwen/Qwen3-30B-A3B
5
  library_name: transformers
6
  tags:
7
  - mergekit
 
10
  ---
11
  # CavesOfQwen
12
 
13
+ > Hey Hey, Model Gang, KaraWitch Here.
14
+ > Have you, ever merged too deeply.
15
+ > And found something 'they' don't want you to know?
16
+ > "[MoQ3](https://youtu.be/o_PBfLbd3zw)", who is she? And why can't I reach her?
17
+
18
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
19
 
20
  ## Merge Details
 
47
  parameters:
48
  normalize: true
49
  dtype: bfloat16
50
+ ```