Hugging Face's logo

Darkhn
/
Legion-V1.9-LLaMa-70B-6.0bpw-exl2-h8

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
6-bit
exl2
Model card Files Community
Darkhn commited on
Commit
0950a0a
·
verified ·
1 Parent(s): 8842160

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -50
README.md CHANGED
@@ -1,50 +1,44 @@
1
- ---
2
- base_model:
3
- - TareksLab/M-BASE-SCE
4
- - TareksLab/M-MERGE2
5
- - TareksLab/M-MERGE4
6
- - TareksLab/M-MERGE1
7
- - TareksLab/M-MERGE3
8
- library_name: transformers
9
- tags:
10
- - mergekit
11
- - merge
12
-
13
- ---
14
- # merge
15
-
16
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
-
18
- ## Merge Details
19
- ### Merge Method
20
-
21
- This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [TareksLab/M-BASE-SCE](https://huggingface.co/TareksLab/M-BASE-SCE) as a base.
22
-
23
- ### Models Merged
24
-
25
- The following models were included in the merge:
26
- * [TareksLab/M-MERGE2](https://huggingface.co/TareksLab/M-MERGE2)
27
- * [TareksLab/M-MERGE4](https://huggingface.co/TareksLab/M-MERGE4)
28
- * [TareksLab/M-MERGE1](https://huggingface.co/TareksLab/M-MERGE1)
29
- * [TareksLab/M-MERGE3](https://huggingface.co/TareksLab/M-MERGE3)
30
-
31
- ### Configuration
32
-
33
- The following YAML configuration was used to produce this model:
34
-
35
- ```yaml
36
- models:
37
- - model: TareksLab/M-MERGE4
38
- - model: TareksLab/M-MERGE3
39
- - model: TareksLab/M-MERGE2
40
- - model: TareksLab/M-MERGE1
41
- merge_method: sce
42
- base_model: TareksLab/M-BASE-SCE
43
- parameters:
44
- select_topk: 0.16
45
- int8_mask: true
46
- chat_template: llama3
47
- tokenizer:
48
- source: TareksLab/M-TOKENIZER-SCE
49
- dtype: bfloat16
50
- ```
 
1
+ ---
2
+ base_model_relation: quantized
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+ ---
8
+ # merge
9
+
10
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
11
+
12
+ ## Merge Details
13
+ ### Merge Method
14
+
15
+ This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [TareksLab/M-BASE-SCE](https://huggingface.co/TareksLab/M-BASE-SCE) as a base.
16
+
17
+ ### Models Merged
18
+
19
+ The following models were included in the merge:
20
+ * [TareksLab/M-MERGE2](https://huggingface.co/TareksLab/M-MERGE2)
21
+ * [TareksLab/M-MERGE4](https://huggingface.co/TareksLab/M-MERGE4)
22
+ * [TareksLab/M-MERGE1](https://huggingface.co/TareksLab/M-MERGE1)
23
+ * [TareksLab/M-MERGE3](https://huggingface.co/TareksLab/M-MERGE3)
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ models:
31
+ - model: TareksLab/M-MERGE4
32
+ - model: TareksLab/M-MERGE3
33
+ - model: TareksLab/M-MERGE2
34
+ - model: TareksLab/M-MERGE1
35
+ merge_method: sce
36
+ base_model: TareksLab/M-BASE-SCE
37
+ parameters:
38
+ select_topk: 0.16
39
+ int8_mask: true
40
+ chat_template: llama3
41
+ tokenizer:
42
+ source: TareksLab/M-TOKENIZER-SCE
43
+ dtype: bfloat16
44
+ ```