Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,45 @@ Good Evening.
|
|
| 5 |
|
| 6 |
New model mix because I got frustrated of dealing with wrangling with parameters and I chalked it up to a "Seems like a model issue".
|
| 7 |
|
| 8 |
-
Going back to merge stock since i dont feel like experimenting and want to try something that vibes well out of the box.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
New model mix because I got frustrated of dealing with wrangling with parameters and I chalked it up to a "Seems like a model issue".
|
| 7 |
|
| 8 |
+
Going back to merge stock since i dont feel like experimenting and want to try something that vibes well out of the box.
|
| 9 |
+
|
| 10 |
+
## Merge Details
|
| 11 |
+
### Merge Method
|
| 12 |
+
|
| 13 |
+
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using Llama-3.3-70B-Instruct as a base.
|
| 14 |
+
|
| 15 |
+
### Models Merged
|
| 16 |
+
|
| 17 |
+
The following models were included in the merge:
|
| 18 |
+
* [KaraKaraWitch/Llama-MiraiFanfare-2-3.3-70B](https://huggingface.co/KaraKaraWitch/Llama-MiraiFanfare-2-3.3-70B)
|
| 19 |
+
* [Undi95/Sushi-v1.4](https://huggingface.co/Undi95/Sushi-v1.4)
|
| 20 |
+
* [Nohobby/L3.3-Prikol-70B-v0.2](https://huggingface.co/Nohobby/L3.3-Prikol-70B-v0.2)
|
| 21 |
+
* [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)
|
| 22 |
+
* [TheDrummer/Anubis-70B-v1](https://huggingface.co/TheDrummer/Anubis-70B-v1)
|
| 23 |
+
* [EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1)
|
| 24 |
+
* [nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1](https://huggingface.co/nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1)
|
| 25 |
+
* [Blackroot/Mirai-3.0-70B](https://huggingface.co/Blackroot/Mirai-3.0-70B)
|
| 26 |
+
* [Sao10K/70B-L3.3-Cirrus-x1](https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1)
|
| 27 |
+
|
| 28 |
+
### Configuration
|
| 29 |
+
|
| 30 |
+
The following YAML configuration was used to produce this model:
|
| 31 |
+
|
| 32 |
+
```yaml
|
| 33 |
+
models:
|
| 34 |
+
- model: Blackroot/Mirai-3.0-70B
|
| 35 |
+
- model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
|
| 36 |
+
- model: TheDrummer/Anubis-70B-v1
|
| 37 |
+
- model: Sao10K/L3.3-70B-Euryale-v2.3
|
| 38 |
+
- model: Sao10K/70B-L3.3-Cirrus-x1
|
| 39 |
+
- model: nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1
|
| 40 |
+
- model: KaraKaraWitch/Llama-MiraiFanfare-2-3.3-70B
|
| 41 |
+
- model: Undi95/Sushi-v1.4
|
| 42 |
+
- model: Nohobby/L3.3-Prikol-70B-v0.2
|
| 43 |
+
|
| 44 |
+
merge_method: model_stock
|
| 45 |
+
base_model: Llama-3.3-70B-Instruct
|
| 46 |
+
parameters:
|
| 47 |
+
normalize: true
|
| 48 |
+
dtype: bfloat16
|
| 49 |
+
```
|