Update README.md
Browse files
README.md
CHANGED
@@ -16,13 +16,6 @@ tags:
|
|
16 |
---
|
17 |
# U-GO-GIRL-Remix-Llama-3-KoEn-8B
|
18 |
|
19 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
20 |
-
|
21 |
-
## Merge Details
|
22 |
-
### Merge Method
|
23 |
-
|
24 |
-
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|
25 |
-
|
26 |
### Models Merged
|
27 |
|
28 |
The following models were included in the merge:
|
@@ -33,54 +26,3 @@ The following models were included in the merge:
|
|
33 |
* [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
|
34 |
* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
|
35 |
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
|
36 |
-
|
37 |
-
### Configuration
|
38 |
-
|
39 |
-
The following YAML configuration was used to produce this model:
|
40 |
-
|
41 |
-
```yaml
|
42 |
-
models:
|
43 |
-
- model: NousResearch/Meta-Llama-3-8B
|
44 |
-
# Base model providing a general foundation without specific parameters
|
45 |
-
- model: NousResearch/Meta-Llama-3-8B-Instruct
|
46 |
-
parameters:
|
47 |
-
density: 0.65
|
48 |
-
weight: 0.4
|
49 |
-
|
50 |
-
- model: asiansoul/U-GO-GIRL-Llama-3-KoEn-8B
|
51 |
-
parameters:
|
52 |
-
density: 0.6
|
53 |
-
weight: 0.3
|
54 |
-
|
55 |
-
- model: allganize/Llama-3-Alpha-Ko-8B-Instruct
|
56 |
-
parameters:
|
57 |
-
density: 0.55
|
58 |
-
weight: 0.1
|
59 |
-
|
60 |
-
- model: saltlux/Ko-Llama3-Luxia-8B
|
61 |
-
parameters:
|
62 |
-
density: 0.55
|
63 |
-
weight: 0.1
|
64 |
-
|
65 |
-
- model: nayohan/llama3-instrucTrans-enko-8b
|
66 |
-
parameters:
|
67 |
-
density: 0.55
|
68 |
-
weight: 0.1
|
69 |
-
|
70 |
-
- model: rombodawg/Llama-3-8B-Instruct-Coder
|
71 |
-
parameters:
|
72 |
-
density: 0.55
|
73 |
-
weight: 0.05
|
74 |
-
|
75 |
-
- model: NousResearch/Hermes-2-Theta-Llama-3-8B
|
76 |
-
parameters:
|
77 |
-
density: 0.55
|
78 |
-
weight: 0.05
|
79 |
-
|
80 |
-
merge_method: dare_ties
|
81 |
-
base_model: NousResearch/Meta-Llama-3-8B
|
82 |
-
parameters:
|
83 |
-
int8_mask: true
|
84 |
-
dtype: bfloat16
|
85 |
-
|
86 |
-
```
|
|
|
16 |
---
|
17 |
# U-GO-GIRL-Remix-Llama-3-KoEn-8B
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
### Models Merged
|
20 |
|
21 |
The following models were included in the merge:
|
|
|
26 |
* [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
|
27 |
* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
|
28 |
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|