bamec66557 commited on
Commit
eb53d01
·
verified ·
1 Parent(s): 199affb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -66
README.md CHANGED
@@ -1,66 +1,66 @@
1
- ---
2
- base_model: []
3
- library_name: transformers
4
- tags:
5
- - mergekit
6
- - merge
7
-
8
- ---
9
- # Z-2-A.TEST-TEMP-MODEL
10
-
11
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
-
13
- ## Merge Details
14
- ### Merge Method
15
-
16
- This model was merged using the SLERP merge method.
17
-
18
- ### Models Merged
19
-
20
- The following models were included in the merge:
21
- * D:\VICIOUS_MESH-12B-OMEGA
22
- * D:\jetreessence
23
-
24
- ### Configuration
25
-
26
- The following YAML configuration was used to produce this model:
27
-
28
- ```yaml
29
- models:
30
- - model: "D:\\VICIOUS_MESH-12B-OMEGA"
31
- - model: "D:\\jetreessence"
32
- merge_method: slerp
33
- base_model: "D:\\VICIOUS_MESH-12B-OMEGA"
34
- dtype: bfloat16
35
- parameters:
36
- t: [0, 0.5, 1, 0.5, 0]
37
-
38
- regularization:
39
- - method: gradient_penalty
40
- scale: 0.05
41
- - method: weight_clipping
42
- clip_range: [-0.15, 0.15]
43
- - method: random_noise
44
- scale: 0.01
45
- - method: attention_dropout
46
- scale: 0.02
47
-
48
- postprocessing:
49
- - operation: entropy_regularization
50
- scale: 0.05
51
- - operation: non_linear_scaling
52
- parameters:
53
- function: relu
54
- - operation: sharpening
55
- intensity: 0.6
56
- - operation: gaussian_smoothing
57
- sigma: 0.3
58
- - operation: normalize
59
- - operation: dynamic_scaling
60
- scale_range: [0.98, 1.02]
61
- - operation: smoothing
62
- parameters:
63
- adaptive: true
64
- range: [0.98, 1.02]
65
- kernel_size: 3
66
- ```
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - mergekit
5
+ - merge
6
+ - not-for-all-audiences
7
+ license: apache-2.0
8
+ ---
9
+ # Z-2-A.TEST-TEMP-MODEL
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the SLERP merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * D:\VICIOUS_MESH-12B-OMEGA
22
+ * D:\jetreessence
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ models:
30
+ - model: "D:\\VICIOUS_MESH-12B-OMEGA"
31
+ - model: "D:\\jetreessence"
32
+ merge_method: slerp
33
+ base_model: "D:\\VICIOUS_MESH-12B-OMEGA"
34
+ dtype: bfloat16
35
+ parameters:
36
+ t: [0, 0.5, 1, 0.5, 0]
37
+
38
+ regularization:
39
+ - method: gradient_penalty
40
+ scale: 0.05
41
+ - method: weight_clipping
42
+ clip_range: [-0.15, 0.15]
43
+ - method: random_noise
44
+ scale: 0.01
45
+ - method: attention_dropout
46
+ scale: 0.02
47
+
48
+ postprocessing:
49
+ - operation: entropy_regularization
50
+ scale: 0.05
51
+ - operation: non_linear_scaling
52
+ parameters:
53
+ function: relu
54
+ - operation: sharpening
55
+ intensity: 0.6
56
+ - operation: gaussian_smoothing
57
+ sigma: 0.3
58
+ - operation: normalize
59
+ - operation: dynamic_scaling
60
+ scale_range: [0.98, 1.02]
61
+ - operation: smoothing
62
+ parameters:
63
+ adaptive: true
64
+ range: [0.98, 1.02]
65
+ kernel_size: 3
66
+ ```