Upload folder using huggingface_hub
Browse files- README.md +98 -0
- mergekit_config.yml +4 -4
- model-00001-of-00025.safetensors +1 -1
- model-00002-of-00025.safetensors +1 -1
- model-00003-of-00025.safetensors +1 -1
- model-00004-of-00025.safetensors +1 -1
- model-00005-of-00025.safetensors +1 -1
- model-00006-of-00025.safetensors +1 -1
- model-00007-of-00025.safetensors +1 -1
- model-00008-of-00025.safetensors +1 -1
- model-00009-of-00025.safetensors +1 -1
- model-00010-of-00025.safetensors +1 -1
- model-00011-of-00025.safetensors +1 -1
- model-00012-of-00025.safetensors +1 -1
- model-00013-of-00025.safetensors +1 -1
- model-00014-of-00025.safetensors +1 -1
- model-00015-of-00025.safetensors +1 -1
- model-00016-of-00025.safetensors +1 -1
- model-00017-of-00025.safetensors +1 -1
- model-00018-of-00025.safetensors +1 -1
- model-00019-of-00025.safetensors +1 -1
- model-00020-of-00025.safetensors +1 -1
- model-00021-of-00025.safetensors +1 -1
- model-00022-of-00025.safetensors +1 -1
- model-00023-of-00025.safetensors +1 -1
- model-00024-of-00025.safetensors +1 -1
- model-00025-of-00025.safetensors +1 -1
README.md
CHANGED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Nitral-AI/Captain-Eris_Violet-V0.420-12B
|
4 |
+
- alexxi19/ft-v1-nemo-base
|
5 |
+
- anthracite-org/magnum-v2-12b
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
|
11 |
+
---
|
12 |
+
# merged_llm
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
## Merge Details
|
17 |
+
### Merge Method
|
18 |
+
|
19 |
+
This model was merged using the linear [DELLA](https://arxiv.org/abs/2406.11617) merge method using [alexxi19/ft-v1-nemo-base](https://huggingface.co/alexxi19/ft-v1-nemo-base) as a base.
|
20 |
+
|
21 |
+
### Models Merged
|
22 |
+
|
23 |
+
The following models were included in the merge:
|
24 |
+
* [Nitral-AI/Captain-Eris_Violet-V0.420-12B](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B)
|
25 |
+
* [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b)
|
26 |
+
|
27 |
+
### Configuration
|
28 |
+
|
29 |
+
The following YAML configuration was used to produce this model:
|
30 |
+
|
31 |
+
```yaml
|
32 |
+
# models:
|
33 |
+
# - model: anthracite-org/magnum-v2-12b # instruct model
|
34 |
+
# parameters:
|
35 |
+
# density: 0.6
|
36 |
+
# weight: 0.5
|
37 |
+
# # - model: /home/paperspace/projects/project/finetunellm/outputs/nemo-12b-creative/merged # creative writing model
|
38 |
+
# # parameters:
|
39 |
+
# # density: 0.3
|
40 |
+
# # weight: 0.3
|
41 |
+
# - model: alexxi19/ft-nemo-base-lora # sft model
|
42 |
+
# parameters:
|
43 |
+
# density: 0.7
|
44 |
+
# weight: 0.5
|
45 |
+
# merge_method: dare_ties
|
46 |
+
# base_model: alexxi19/ft-nemo-base-lora
|
47 |
+
# parameters:
|
48 |
+
# int8_mask: true
|
49 |
+
# rescale: true
|
50 |
+
# # normalize: true
|
51 |
+
# dtype: bfloat16
|
52 |
+
# chat_template: chatml
|
53 |
+
|
54 |
+
|
55 |
+
models:
|
56 |
+
- model: anthracite-org/magnum-v2-12b # instruct model
|
57 |
+
parameters:
|
58 |
+
density: 0.3
|
59 |
+
weight: 0.5
|
60 |
+
# - model: Nitral-AI/Captain_BMO-12B # instruct model
|
61 |
+
# parameters:
|
62 |
+
# density: 0.3
|
63 |
+
# weight: 0.5
|
64 |
+
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B # creative writing model
|
65 |
+
parameters:
|
66 |
+
density: 0.2
|
67 |
+
weight: 0.3
|
68 |
+
- model: alexxi19/ft-v1-nemo-base # sft model
|
69 |
+
parameters:
|
70 |
+
density: 0.5
|
71 |
+
weight: 0.5
|
72 |
+
base_model: alexxi19/ft-v1-nemo-base
|
73 |
+
dtype: bfloat16
|
74 |
+
chat_template: chatml
|
75 |
+
merge_method: della_linear
|
76 |
+
parameters:
|
77 |
+
epsilon: 0.05
|
78 |
+
int8_mask: true
|
79 |
+
rescale: true
|
80 |
+
lambda: 1.0
|
81 |
+
|
82 |
+
|
83 |
+
# models:
|
84 |
+
# - model: Nitral-AI/Captain_BMO-12B # another sft model
|
85 |
+
# - model: alexxi19/ft-v1-nemo-base # sft model
|
86 |
+
# merge_method: slerp
|
87 |
+
# base_model: alexxi19/ft-v1-nemo-base
|
88 |
+
# parameters:
|
89 |
+
# t:
|
90 |
+
# - filter: self_attn
|
91 |
+
# value: [0, 0.5, 0.3, 0.7, 1]
|
92 |
+
# - filter: mlp
|
93 |
+
# value: [1, 0.5, 0.7, 0.3, 0]
|
94 |
+
# - value: 0.3 # fallback for rest of tensors
|
95 |
+
# dtype: float16
|
96 |
+
# chat_template: chatml
|
97 |
+
|
98 |
+
```
|
mergekit_config.yml
CHANGED
@@ -26,10 +26,10 @@ models:
|
|
26 |
parameters:
|
27 |
density: 0.3
|
28 |
weight: 0.5
|
29 |
-
- model: Nitral-AI/Captain_BMO-12B # instruct model
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B # creative writing model
|
34 |
parameters:
|
35 |
density: 0.2
|
|
|
26 |
parameters:
|
27 |
density: 0.3
|
28 |
weight: 0.5
|
29 |
+
# - model: Nitral-AI/Captain_BMO-12B # instruct model
|
30 |
+
# parameters:
|
31 |
+
# density: 0.3
|
32 |
+
# weight: 0.5
|
33 |
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B # creative writing model
|
34 |
parameters:
|
35 |
density: 0.2
|
model-00001-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342177408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:108affc8d24fcd992171f56e8d2edd81f5dd09f9cae0873f3fcd9fc615d50591
|
3 |
size 1342177408
|
model-00002-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342177424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f199bc51fc9a281f47da7601541f7db87e02df12c0f89efb82fcb13ec4d66fc
|
3 |
size 1342177424
|
model-00003-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996189888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b806586cd71bfe471c9cf3cf7b8757a33c04b6f8ca01ead6eaa7bd912e1a234
|
3 |
size 996189888
|
model-00004-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a409a3fd94e640d7a47685b81fbf28594cf9d20d71aa9408243f5e78d8b228
|
3 |
size 933265104
|
model-00005-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96f14b68f2e061603732d6eb8992384f0faadaec7e6da4335974bdbea844c9a9
|
3 |
size 943761344
|
model-00006-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:526c0d636acddb438b311b3ede3936ca92a48c3c4508064544adbb03e1b74505
|
3 |
size 943761344
|
model-00007-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996179560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0233fd66040b8564cae8487155b98bc9dc7e39e4e755514f0887b80006b4e7e7
|
3 |
size 996179560
|
model-00008-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e1a34d52d49ef859b73672ee9f4e9f6c99986cc2b577c6ce4de2d9124cacd20
|
3 |
size 933265104
|
model-00009-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b008530bbd44acf16646bb14e9fdd0b39d322696014f73d6ae3bb96637ae3a6
|
3 |
size 943761344
|
model-00010-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eb8348f50d3199371ae5933e514a183a1b71752e1663029431b3587cf0ad052
|
3 |
size 943761344
|
model-00011-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996179560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068c8cbc978d80180f4f3f3be1d382d43c0f5323a713b8290f627d3000f2eee0
|
3 |
size 996179560
|
model-00012-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027b79e1995c11af05cdfd35d5cebeb737de7229078ac61edd7c48d42b415a0b
|
3 |
size 933265104
|
model-00013-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caacaa115632ed4a0f21b67c2e4d78b2c7738b51fbe951ccbf178a520642533e
|
3 |
size 943761344
|
model-00014-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f02fbfae03aa00da0ccbf9b534720b4c4b7c20c460a76be76be9c0e723c31d9
|
3 |
size 943761344
|
model-00015-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996179560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:226e20c12a80d2aaa03f4ccab94a8856d034861faaab44d1e476b6f1954aced4
|
3 |
size 996179560
|
model-00016-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12736ba86cb4b8d69af457812b2f6aa34d0d267522d34008492c4ffdb2769778
|
3 |
size 933265096
|
model-00017-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71ae2cec08d5d7e31ba0e451ec6e287560c04b85e58f67eb7353d25f91991745
|
3 |
size 943761344
|
model-00018-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6caf29490f7b1232a36ac6de21dbfc591fa7752afe452610fd3b189522f304fe
|
3 |
size 943761344
|
model-00019-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996179560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0a04541daa2feaa059fd013a3ac58c26edb5ccea65870ed3d3147c4cf21b25a
|
3 |
size 996179560
|
model-00020-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bdb93b090c097e5ac5abf5f226d8a47d8f2f932a6899387a3e93ca3ba6274e3
|
3 |
size 933265104
|
model-00021-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4616548382e2a76e4311cb904a3952ed395ccf7e1cad6fbbf054d6fb5f859cd8
|
3 |
size 943761344
|
model-00022-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943761336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1beaa96a302191d9b25e33e37c659eb5a5c9657463765194b387a5eb7f2fe5bf
|
3 |
size 943761336
|
model-00023-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996179552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb4883ac087bacbdf9d77d75640cab1c5bad271fbf58f8f1382595d3c90aa3a6
|
3 |
size 996179552
|
model-00024-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 933265088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f10360e7550aa1ffc9d98b22f6bcf32f957568224e85f81aead34e79812d6a
|
3 |
size 933265088
|
model-00025-of-00025.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 796960560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64559765a3c0fc4a03d72f6149ee2018b638fd0cb79512a2e5bf291b0b44188
|
3 |
size 796960560
|