Update README.md
Browse files
README.md
CHANGED
|
@@ -10,33 +10,12 @@ base_model:
|
|
| 10 |
- llm-jp/llm-jp-1.3b-v1.0
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# llmjp-
|
| 14 |
|
| 15 |
llmjp-slerp2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
| 16 |
* [kcoopermiller/llm-jp-1.3b-v1.0-aya](https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya)
|
| 17 |
* [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
|
| 18 |
|
| 19 |
-
## 🧩 Configuration
|
| 20 |
-
|
| 21 |
-
```yaml
|
| 22 |
-
slices:
|
| 23 |
-
- sources:
|
| 24 |
-
- model: kcoopermiller/llm-jp-1.3b-v1.0-aya
|
| 25 |
-
layer_range: [0, 24]
|
| 26 |
-
- model: llm-jp/llm-jp-1.3b-v1.0
|
| 27 |
-
layer_range: [0, 24]
|
| 28 |
-
merge_method: slerp
|
| 29 |
-
base_model: llm-jp/llm-jp-1.3b-v1.0
|
| 30 |
-
parameters:
|
| 31 |
-
t:
|
| 32 |
-
- filter: self_attn
|
| 33 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
| 34 |
-
- filter: mlp
|
| 35 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
| 36 |
-
- value: 0.5
|
| 37 |
-
dtype: bfloat16
|
| 38 |
-
```
|
| 39 |
-
|
| 40 |
## 💻 Usage
|
| 41 |
|
| 42 |
```python
|
|
|
|
| 10 |
- llm-jp/llm-jp-1.3b-v1.0
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# llmjp-slerp
|
| 14 |
|
| 15 |
llmjp-slerp2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
| 16 |
* [kcoopermiller/llm-jp-1.3b-v1.0-aya](https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya)
|
| 17 |
* [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## 💻 Usage
|
| 20 |
|
| 21 |
```python
|