Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,13 @@ tags:
|
|
7 |
|
8 |
---
|
9 |
# model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
|
@@ -18,9 +25,9 @@ This model was merged using the breadcrumbs_ties merge method using Z:\Llama-3-G
|
|
18 |
### Models Merged
|
19 |
|
20 |
The following models were included in the merge:
|
21 |
-
*
|
22 |
-
*
|
23 |
-
*
|
24 |
|
25 |
### Configuration
|
26 |
|
@@ -28,27 +35,27 @@ The following YAML configuration was used to produce this model:
|
|
28 |
|
29 |
```yaml
|
30 |
models:
|
31 |
-
- model:
|
32 |
parameters:
|
33 |
weight: 0.25
|
34 |
density: 0.90
|
35 |
gamma: 0.01
|
36 |
-
- model:
|
37 |
parameters:
|
38 |
weight: 0.30
|
39 |
density: 0.90
|
40 |
gamma: 0.01
|
41 |
-
- model:
|
42 |
parameters:
|
43 |
weight: 0.15
|
44 |
density: 0.90
|
45 |
gamma: 0.01
|
46 |
-
- model:
|
47 |
parameters:
|
48 |
weight: 0.30
|
49 |
density: 0.90
|
50 |
gamma: 0.01
|
51 |
merge_method: breadcrumbs_ties
|
52 |
-
base_model:
|
53 |
dtype: bfloat16
|
54 |
```
|
|
|
7 |
|
8 |
---
|
9 |
# model
|
10 |
+
A large context uncencored Llama 3 model focussed on story & RP
|
11 |
+
I found the Smaug version of lama very impressive, exept for a couple of quirks and the default context window.
|
12 |
+
This merge is with the Giraffe instruct for long context window, and basically a smaug - lumi tess merger.
|
13 |
+
I am planning to do the same with a gradient model and compaire it to this giraffe version.
|
14 |
+
|
15 |
+
Breadcrumbs_ties really is awesome.
|
16 |
+
|
17 |
|
18 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
19 |
|
|
|
25 |
### Models Merged
|
26 |
|
27 |
The following models were included in the merge:
|
28 |
+
* \Smaug-Llama-3-70B-Instruct
|
29 |
+
* \Llama-3-Lumimaid-70B-v0.1-alt
|
30 |
+
* \Tess-2.0-Llama-3-70B-v0.2
|
31 |
|
32 |
### Configuration
|
33 |
|
|
|
35 |
|
36 |
```yaml
|
37 |
models:
|
38 |
+
- model: \Llama-3-Giraffe-70B-Instruct
|
39 |
parameters:
|
40 |
weight: 0.25
|
41 |
density: 0.90
|
42 |
gamma: 0.01
|
43 |
+
- model: \Smaug-Llama-3-70B-Instruct
|
44 |
parameters:
|
45 |
weight: 0.30
|
46 |
density: 0.90
|
47 |
gamma: 0.01
|
48 |
+
- model: \Tess-2.0-Llama-3-70B-v0.2
|
49 |
parameters:
|
50 |
weight: 0.15
|
51 |
density: 0.90
|
52 |
gamma: 0.01
|
53 |
+
- model: \Llama-3-Lumimaid-70B-v0.1-alt
|
54 |
parameters:
|
55 |
weight: 0.30
|
56 |
density: 0.90
|
57 |
gamma: 0.01
|
58 |
merge_method: breadcrumbs_ties
|
59 |
+
base_model: \Llama-3-Giraffe-70B-Instruct
|
60 |
dtype: bfloat16
|
61 |
```
|