automerger
commited on
Commit
•
d3a3d90
1
Parent(s):
afad297
Upload folder using huggingface_hub
Browse files- README.md +10 -16
- config.json +1 -1
- mergekit_config.yml +9 -14
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -6,37 +6,31 @@ tags:
|
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
9 |
-
- nlpguy/AlloyIngotNeoY
|
10 |
- Kukedlc/NeuralSirKrishna-7b
|
11 |
---
|
12 |
|
13 |
# AlloyingotneoyNeuralsirkrishna-7B
|
14 |
|
15 |
AlloyingotneoyNeuralsirkrishna-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
16 |
-
* [nlpguy/AlloyIngotNeoY](https://huggingface.co/nlpguy/AlloyIngotNeoY)
|
17 |
* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b)
|
18 |
|
19 |
## 🧩 Configuration
|
20 |
|
21 |
```yaml
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
|
|
29 |
base_model: nlpguy/AlloyIngotNeoY
|
30 |
parameters:
|
31 |
-
|
32 |
-
- filter: self_attn
|
33 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
-
- filter: mlp
|
35 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
-
- value: 0.5
|
37 |
dtype: bfloat16
|
38 |
random_seed: 0
|
39 |
-
|
40 |
|
41 |
## 💻 Usage
|
42 |
|
|
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
|
|
9 |
- Kukedlc/NeuralSirKrishna-7b
|
10 |
---
|
11 |
|
12 |
# AlloyingotneoyNeuralsirkrishna-7B
|
13 |
|
14 |
AlloyingotneoyNeuralsirkrishna-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
|
|
15 |
* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b)
|
16 |
|
17 |
## 🧩 Configuration
|
18 |
|
19 |
```yaml
|
20 |
+
models:
|
21 |
+
- model: nlpguy/AlloyIngotNeoY
|
22 |
+
# No parameters necessary for base model
|
23 |
+
- model: Kukedlc/NeuralSirKrishna-7b
|
24 |
+
parameters:
|
25 |
+
density: 0.53
|
26 |
+
weight: 0.6
|
27 |
+
merge_method: dare_ties
|
28 |
base_model: nlpguy/AlloyIngotNeoY
|
29 |
parameters:
|
30 |
+
int8_mask: true
|
|
|
|
|
|
|
|
|
|
|
31 |
dtype: bfloat16
|
32 |
random_seed: 0
|
33 |
+
```
|
34 |
|
35 |
## 💻 Usage
|
36 |
|
config.json
CHANGED
@@ -21,7 +21,7 @@
|
|
21 |
"sliding_window": 4096,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
21 |
"sliding_window": 4096,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.39.0",
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 32000
|
27 |
}
|
mergekit_config.yml
CHANGED
@@ -1,19 +1,14 @@
|
|
1 |
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
|
|
9 |
base_model: nlpguy/AlloyIngotNeoY
|
10 |
parameters:
|
11 |
-
|
12 |
-
- filter: self_attn
|
13 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
-
- filter: mlp
|
15 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
-
- value: 0.5
|
17 |
dtype: bfloat16
|
18 |
random_seed: 0
|
19 |
-
|
|
|
1 |
|
2 |
+
models:
|
3 |
+
- model: nlpguy/AlloyIngotNeoY
|
4 |
+
# No parameters necessary for base model
|
5 |
+
- model: Kukedlc/NeuralSirKrishna-7b
|
6 |
+
parameters:
|
7 |
+
density: 0.53
|
8 |
+
weight: 0.6
|
9 |
+
merge_method: dare_ties
|
10 |
base_model: nlpguy/AlloyIngotNeoY
|
11 |
parameters:
|
12 |
+
int8_mask: true
|
|
|
|
|
|
|
|
|
|
|
13 |
dtype: bfloat16
|
14 |
random_seed: 0
|
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9825524456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04579ef4cdfc587466d43f0bc612812490fdef88e80fb49fee3b2a97b549871
|
3 |
size 9825524456
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4657973592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84db58379e13e5ce65486c57b37d136c5d88ed144cbbb42381864a78032c3565
|
3 |
size 4657973592
|