Triangle104 commited on
Commit
7625cce
·
verified ·
1 Parent(s): 330d550

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -12,6 +12,69 @@ tags:
12
  This model was converted to GGUF format from [`ProdeusUnity/Stellar-Odyssey-12b-v0.0`](https://huggingface.co/ProdeusUnity/Stellar-Odyssey-12b-v0.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
13
  Refer to the [original model card](https://huggingface.co/ProdeusUnity/Stellar-Odyssey-12b-v0.0) for more details on the model.
14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ## Use with llama.cpp
16
  Install llama.cpp through brew (works on Mac and Linux)
17
 
 
12
  This model was converted to GGUF format from [`ProdeusUnity/Stellar-Odyssey-12b-v0.0`](https://huggingface.co/ProdeusUnity/Stellar-Odyssey-12b-v0.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
13
  Refer to the [original model card](https://huggingface.co/ProdeusUnity/Stellar-Odyssey-12b-v0.0) for more details on the model.
14
 
15
+ ---
16
+ Model details:
17
+ -
18
+ Stellar Odyssey 12b v0.0
19
+
20
+ We will see... Come with me, take the journey~
21
+
22
+ Listen to the song on Youtube: https://www.youtube.com/watch?v=3FEFtFMBREA
23
+
24
+ Soo... after I failed the first time, I took a crack at merging again. This time, these models were used
25
+
26
+ mistralai/Mistral-Nemo-Base-2407 Sao10K/MN-12B-Lyra-v4 nothingiisreal/MN-12B-Starcannon-v2 Gryphe/Pantheon-RP-1.5-12b-Nemo
27
+
28
+ License for this model is: cc-by-nc-4.0
29
+
30
+ TO CLEAR SOME CONFUSION: Please use ChatML I hope this was worth the time I spent to create this merge, lol
31
+
32
+ Gated access for now, gated access will be disabled when testing is done, and thanks to all who have interest.
33
+
34
+ Thank you to AuriAetherwiing for helping me merge the models.
35
+
36
+ Details
37
+
38
+ This is a merge of pre-trained language models created using mergekit.
39
+ Merge Details
40
+ Merge Method
41
+
42
+ This model was merged using the della_linear merge method using C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\mistralai_Mistral-Nemo-Base-2407 as a base.
43
+ Models Merged
44
+
45
+ The following models were included in the merge:
46
+
47
+ C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\Sao10K_MN-12B-Lyra-v4
48
+ C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.5-12b-Nemo
49
+ C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\nothingiisreal_MN-12B-Starcannon-v2
50
+
51
+ Configuration
52
+
53
+ The following YAML configuration was used to produce this model:
54
+
55
+ models:
56
+ - model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Sao10K_MN-12B-Lyra-v4
57
+ parameters:
58
+ weight: 0.3
59
+ density: 0.25
60
+ - model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\nothingiisreal_MN-12B-Starcannon-v2
61
+ parameters:
62
+ weight: 0.1
63
+ density: 0.4
64
+ - model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.5-12b-Nemo
65
+ parameters:
66
+ weight: 0.4
67
+ density: 0.5
68
+ merge_method: della_linear
69
+ base_model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\mistralai_Mistral-Nemo-Base-2407
70
+ parameters:
71
+ epsilon: 0.05
72
+ lambda: 1
73
+ merge_method: della_linear
74
+ dtype: bfloat16
75
+
76
+ ---
77
+
78
  ## Use with llama.cpp
79
  Install llama.cpp through brew (works on Mac and Linux)
80