Update README.md
Browse files
README.md
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- DiscoResearch/
|
4 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
- meta-llama/Meta-Llama-3-8B
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
10 |
-
|
11 |
---
|
12 |
-
#
|
13 |
|
14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
|
@@ -21,7 +21,7 @@ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](
|
|
21 |
### Models Merged
|
22 |
|
23 |
The following models were included in the merge:
|
24 |
-
* [DiscoResearch/
|
25 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
26 |
|
27 |
### Configuration
|
@@ -30,7 +30,7 @@ The following YAML configuration was used to produce this model:
|
|
30 |
|
31 |
```yaml
|
32 |
models:
|
33 |
-
- model: DiscoResearch/
|
34 |
parameters:
|
35 |
density: 0.5
|
36 |
weight: 0.5
|
@@ -45,4 +45,4 @@ parameters:
|
|
45 |
int8_mask: false
|
46 |
dtype: bfloat16
|
47 |
|
48 |
-
```
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
+
- DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1
|
4 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
- meta-llama/Meta-Llama-3-8B
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
10 |
+
license: llama3
|
11 |
---
|
12 |
+
# Llama3_DiscoLeo_8B_DARE_Experimental
|
13 |
|
14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
|
|
|
21 |
### Models Merged
|
22 |
|
23 |
The following models were included in the merge:
|
24 |
+
* [DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1](https://huggingface.co/DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1)
|
25 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
26 |
|
27 |
### Configuration
|
|
|
30 |
|
31 |
```yaml
|
32 |
models:
|
33 |
+
- model: DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1
|
34 |
parameters:
|
35 |
density: 0.5
|
36 |
weight: 0.5
|
|
|
45 |
int8_mask: false
|
46 |
dtype: bfloat16
|
47 |
|
48 |
+
```
|