ray0rf1re commited on
Commit
216dcbd
·
verified ·
1 Parent(s): 1cbb7d4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -42
README.md CHANGED
@@ -1,42 +1,43 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-3B-Instruct
4
- - ray0rf1re/Nix1.5
5
- library_name: transformers
6
- tags:
7
- - mergekit
8
- - merge
9
-
10
- ---
11
- # merged_nix_2.0
12
-
13
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
-
15
- ## Merge Details
16
- ### Merge Method
17
-
18
- This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) as a base.
19
-
20
- ### Models Merged
21
-
22
- The following models were included in the merge:
23
- * [ray0rf1re/Nix1.5](https://huggingface.co/ray0rf1re/Nix1.5)
24
-
25
- ### Configuration
26
-
27
- The following YAML configuration was used to produce this model:
28
-
29
- ```yaml
30
- models:
31
- - model: Qwen/Qwen2.5-3B-Instruct
32
- - model: ray0rf1re/Nix1.5
33
- parameters:
34
- density: 0.40
35
- weight: 0.40
36
- merge_method: ties
37
- base_model: Qwen/Qwen2.5-3B-Instruct
38
- parameters:
39
- normalize: true
40
- int8_mask: true
41
- dtype: float16
42
- ```
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-3B-Instruct
4
+ - ray0rf1re/Nix1.5
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merged_nix_2.0
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) as a base.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [ray0rf1re/Nix1.5](https://huggingface.co/ray0rf1re/Nix1.5)
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ models:
31
+ - model: Qwen/Qwen2.5-3B-Instruct
32
+ - model: ray0rf1re/Nix1.5
33
+ parameters:
34
+ density: 0.40
35
+ weight: 0.40
36
+ merge_method: ties
37
+ base_model: Qwen/Qwen2.5-3B-Instruct
38
+ parameters:
39
+ normalize: true
40
+ int8_mask: true
41
+ dtype: float16
42
+ ```
43
+ i call it "halusigins"