rombodawg commited on
Commit
e743cee
1 Parent(s): c3da282

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md CHANGED
@@ -2,4 +2,87 @@
2
  license: other
3
  license_name: gemma-terms-of-use
4
  license_link: https://ai.google.dev/gemma/terms
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: other
3
  license_name: gemma-terms-of-use
4
  license_link: https://ai.google.dev/gemma/terms
5
+
6
+ tags:
7
+ - merge
8
  ---
9
+ EveryoneLLM-7b-Gemma-Base
10
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/85jTMkzdKWv4V8aQntMY-.jpeg)
11
+
12
+
13
+ EveryoneLLM series of models made by the community, for the community.
14
+
15
+ This is the second version of Everyone-LLM using Gemma-7b, a model that combines the power of the large majority of powerfull fine-tuned LLM's made by the community, to create a vast and knowledgable LLM with various abilities with an extra emphasis on coding capabilities.
16
+
17
+
18
+ Prompt template: Alpaca
19
+ ```
20
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
21
+ ### Instruction:
22
+ {prompt}
23
+ ### Response:
24
+ ```
25
+
26
+
27
+ The models that were used in this merger were as follow:
28
+
29
+ - https://huggingface.co/openchat/openchat-3.5-0106-gemma
30
+
31
+ - https://huggingface.co/TechxGenus/CodeGemma-7b
32
+
33
+ - https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b
34
+
35
+ - https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo
36
+
37
+ - https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1
38
+
39
+ - https://huggingface.co/CorticalStack/gemma-7b-ultrachat-sft
40
+
41
+ - https://huggingface.co/google/gemma-7b
42
+
43
+ Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗
44
+
45
+ This model was merges in 2 parts. The order of parts is listed bellow, then a copy and pastable version is bellow that.
46
+
47
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/Ctla5otlla8UaTgW9fODc.png)
48
+
49
+ ```yaml
50
+ models:
51
+ - model: VAGOsolutions_SauerkrautLM-Gemma-7b
52
+ parameters:
53
+ weight: 1
54
+ - model: macadeliccc_gemma-orchid-7b-dpo
55
+ parameters:
56
+ weight: 1
57
+ - model: HuggingFaceH4_zephyr-7b-gemma-v0.1
58
+ parameters:
59
+ weight: 1
60
+ - model: CorticalStack_gemma-7b-ultrachat-sft
61
+ parameters:
62
+ weight: 1
63
+ merge_method: task_arithmetic
64
+ base_model: gemma-7b-base
65
+ parameters:
66
+ normalize: true
67
+ int8_mask: true
68
+ dtype: float16
69
+ ```
70
+
71
+ ```yaml
72
+ models:
73
+ - model: Gemma-Merge-1-7b
74
+ parameters:
75
+ weight: 1
76
+ - model: openchat_openchat-3.5-0106-gemma
77
+ parameters:
78
+ weight: 1
79
+ - model: TechxGenus_CodeGemma-7b
80
+ parameters:
81
+ weight: 1
82
+ merge_method: task_arithmetic
83
+ base_model: gemma-7b-base
84
+ parameters:
85
+ normalize: true
86
+ int8_mask: true
87
+ dtype: float16
88
+ ```