Update README.md
Browse files
README.md
CHANGED
@@ -1,51 +1,26 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
tags:
|
5 |
-
-
|
|
|
|
|
6 |
- merge
|
7 |
-
|
8 |
---
|
9 |
-
# out
|
10 |
-
|
11 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
-
|
13 |
-
## Merge Details
|
14 |
-
### Merge Method
|
15 |
-
|
16 |
-
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated as a base.
|
17 |
-
|
18 |
-
### Models Merged
|
19 |
-
|
20 |
-
The following models were included in the merge:
|
21 |
-
* /mnt/bigly/fp16/Llama3-PBM-Nova-70B
|
22 |
-
* /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
|
23 |
-
* /mnt/ue/fp16-2/BaseModelsMerged
|
24 |
-
* /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3
|
25 |
-
|
26 |
-
### Configuration
|
27 |
|
28 |
-
|
|
|
29 |
|
30 |
-
|
31 |
-
merge_method: ties
|
32 |
-
base_model: /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
|
33 |
-
models:
|
34 |
-
- model: /mnt/bigly/fp16/Llama3-PBM-Nova-70B
|
35 |
-
parameters:
|
36 |
-
weight: 1.0
|
37 |
-
density: 0.7
|
38 |
-
- model: /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
|
39 |
-
parameters:
|
40 |
-
weight: 1.0
|
41 |
-
density: 0.7
|
42 |
-
- model: /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3
|
43 |
-
parameters:
|
44 |
-
weight: 1.0
|
45 |
-
density: 0.7
|
46 |
-
- model: /mnt/ue/fp16-2/BaseModelsMerged
|
47 |
-
parameters:
|
48 |
-
weight: 1.0
|
49 |
-
density: 0.7
|
50 |
-
dtype: float16
|
51 |
-
```
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
|
4 |
+
- Sao10K/L3.3-70B-Euryale-v2.3
|
5 |
+
- rinna/llama-3-youko-70B
|
6 |
+
- yentinglin/Llama-3-Taiwan-70B-Instruct
|
7 |
+
- meta-llama/Meta-Llama-3-70B
|
8 |
+
- PKU-Baichuan-MLSystemLab/Llama3-PBM-Nova-70B
|
9 |
+
- tokyotech-llm/Llama-3.1-Swallow-70B-v0.1
|
10 |
+
- Bllossom/llama-3-Korean-Bllossom-70B
|
11 |
+
- WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-70B
|
12 |
+
- TsinghuaC3I/Llama-3-70B-UltraMedical
|
13 |
+
- hitachi-nlp/Llama-3.1-70B-FLDx2
|
14 |
+
- PKU-Alignment/ProgressGym-HistLlama3-70B-C013-pretrain-v0.1
|
15 |
+
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
|
16 |
tags:
|
17 |
+
- roleplay
|
18 |
+
- experimental
|
19 |
+
- indie
|
20 |
- merge
|
|
|
21 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
+

|
24 |
+
[](https://discord.gg/2JhHVh7CGu)
|
25 |
|
26 |
+
# Evolution ?
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|