wwe180 commited on
Commit
3f073cf
1 Parent(s): 0917afd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -32
README.md CHANGED
@@ -13,39 +13,11 @@ base_model:
13
  - hfl/llama-3-chinese-8b-instruct-v2
14
  ---
15
 
16
- # Llama3-15B-lingyang-v0.1
 
17
 
18
- Llama3-15B-lingyang-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
- * [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)
20
- * [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
21
- * [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)
22
- * [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
23
- * [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)
24
-
25
- ## 🧩 Configuration
26
-
27
- ```yaml
28
- slices:
29
- - sources:
30
- - model: "hfl/llama-3-chinese-8b-instruct-v2"
31
- layer_range: [0, 10]
32
- - sources:
33
- - model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
34
- layer_range: [0, 20]
35
- - sources:
36
- - model: "hfl/llama-3-chinese-8b-instruct-v2"
37
- layer_range: [10, 20]
38
- - sources:
39
- - model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
40
- layer_range: [20, 32]
41
- - sources:
42
- - model: "hfl/llama-3-chinese-8b-instruct-v2"
43
- layer_range: [20, 32]
44
-
45
- merge_method: passthrough
46
- base_model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
47
- dtype: bfloat16
48
- ```
49
 
50
  ## 💻 Usage
51
 
 
13
  - hfl/llama-3-chinese-8b-instruct-v2
14
  ---
15
 
16
+ # 骆驼3-15B-羚杨-v0.1
17
+ Llama3-15B-lingyang-v0.1 是使用 LazyMergekit 合并以下模型:
18
 
19
+ hfl/llama-3-中文-8b-instruct-v2
20
+ NousResearch/Hermes-2-θ-骆驼-3-8B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  ## 💻 Usage
23