Upload folder using huggingface_hub
Browse files- README.md +37 -0
- model-1.safetensors +3 -0
- model-2.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- codellama/CodeLlama-7b-Python-hf
|
8 |
+
- NousResearch/Llama-2-7b-chat-hf
|
9 |
+
---
|
10 |
+
|
11 |
+
# my-merged-model
|
12 |
+
|
13 |
+
my-merged-model is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
|
15 |
+
* [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
slices:
|
21 |
+
- sources:
|
22 |
+
- model: codellama/CodeLlama-7b-Python-hf
|
23 |
+
layer_range: [0, 32]
|
24 |
+
- model: NousResearch/Llama-2-7b-chat-hf
|
25 |
+
layer_range: [0, 32]
|
26 |
+
merge_method: slerp
|
27 |
+
base_model: codellama/CodeLlama-7b-Python-hf
|
28 |
+
parameters:
|
29 |
+
t:
|
30 |
+
- filter: self_attn
|
31 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
32 |
+
- filter: mlp
|
33 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
34 |
+
- value: 0.5
|
35 |
+
dtype: bfloat16
|
36 |
+
|
37 |
+
```
|
model-1.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b71fa4943c91f92b75d8f7134608214953cea65a9f570b623cfa9783d37763c
|
3 |
+
size 1990275992
|
model-2.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:584267cc8ee0ad90a6b8458e75ddfae41f9c16bb4908ebc1b69550868a4d0c57
|
3 |
+
size 1990284304
|