Update README.md
Browse files
README.md
CHANGED
@@ -20,6 +20,15 @@ This model was merged using the SLERP merge method.
|
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
* [v000000/MN-12B-Part1](https://huggingface.co/v000000/MN-12B-Part1)
|
24 |
* [v000000/MN-12B-Part2](https://huggingface.co/v000000/MN-12B-Part2)
|
25 |
|
@@ -28,6 +37,60 @@ The following models were included in the merge:
|
|
28 |
The following YAML configuration was used to produce this model:
|
29 |
|
30 |
```yaml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
slices:
|
32 |
- sources:
|
33 |
- model: v000000/MN-12B-Part2
|
|
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
+
* [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9)
|
24 |
+
* [shuttleai/shuttle-2.5-mini](https://huggingface.co/shuttleai/shuttle-2.5-mini)
|
25 |
+
* [anthracite-org/magnum-12b-v2](https://huggingface.co/anthracite-org/magnum-12b-v2)
|
26 |
+
* [Sao10K/MN-12B-Lyra-v1](https://huggingface.co/Sao10K/MN-12B-Lyra-v1)
|
27 |
+
* [unsloth/Mistral-Nemo-Instruct-2407](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)
|
28 |
+
* [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B)
|
29 |
+
* [UsernameJustAnother/Nemo-12B-Marlin-v5](https://huggingface.co/UsernameJustAnother/Nemo-12B-Marlin-v5)
|
30 |
+
* [BeaverAI/mistral-doryV2-12b](https://huggingface.co/BeaverAI/mistral-doryV2-12b)
|
31 |
+
* [invisietch/Atlantis-v0.1-12B](https://huggingface.co/invisietch/Atlantis-v0.1-12B)
|
32 |
* [v000000/MN-12B-Part1](https://huggingface.co/v000000/MN-12B-Part1)
|
33 |
* [v000000/MN-12B-Part2](https://huggingface.co/v000000/MN-12B-Part2)
|
34 |
|
|
|
37 |
The following YAML configuration was used to produce this model:
|
38 |
|
39 |
```yaml
|
40 |
+
models:
|
41 |
+
- model: Sao10K/MN-12B-Lyra-v1
|
42 |
+
parameters:
|
43 |
+
weight: 0.15
|
44 |
+
density: 0.77
|
45 |
+
- model: shuttleai/shuttle-2.5-mini
|
46 |
+
parameters:
|
47 |
+
weight: 0.20
|
48 |
+
density: 0.78
|
49 |
+
- model: anthracite-org/magnum-12b-v2
|
50 |
+
parameters:
|
51 |
+
weight: 0.35
|
52 |
+
density: 0.85
|
53 |
+
- model: nothingiisreal/MN-12B-Celeste-V1.9
|
54 |
+
parameters:
|
55 |
+
weight: 0.55
|
56 |
+
density: 0.90
|
57 |
+
merge_method: della
|
58 |
+
base_model: Sao10K/MN-12B-Lyra-v1
|
59 |
+
parameters:
|
60 |
+
int8_mask: true
|
61 |
+
epsilon: 0.05
|
62 |
+
lambda: 1
|
63 |
+
dtype: bfloat16
|
64 |
+
|
65 |
+
models:
|
66 |
+
- model: BeaverAI/mistral-doryV2-12b
|
67 |
+
parameters:
|
68 |
+
weight: 0.10
|
69 |
+
density: 0.4
|
70 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
71 |
+
parameters:
|
72 |
+
weight: 0.20
|
73 |
+
density: 0.4
|
74 |
+
- model: UsernameJustAnother/Nemo-12B-Marlin-v5
|
75 |
+
parameters:
|
76 |
+
weight: 0.25
|
77 |
+
density: 0.5
|
78 |
+
- model: invisietch/Atlantis-v0.1-12B
|
79 |
+
parameters:
|
80 |
+
weight: 0.3
|
81 |
+
density: 0.5
|
82 |
+
- model: NeverSleep/Lumimaid-v0.2-12B
|
83 |
+
parameters:
|
84 |
+
weight: 0.4
|
85 |
+
density: 0.8
|
86 |
+
merge_method: della_linear
|
87 |
+
base_model: anthracite-org/magnum-12b-v2
|
88 |
+
parameters:
|
89 |
+
int8_mask: true
|
90 |
+
epsilon: 0.05
|
91 |
+
lambda: 1
|
92 |
+
dtype: bfloat16
|
93 |
+
|
94 |
slices:
|
95 |
- sources:
|
96 |
- model: v000000/MN-12B-Part2
|