Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- ru
|
6 |
+
tags:
|
7 |
+
- moe
|
8 |
+
---
|
9 |
+
```
|
10 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
11 |
+
gate_mode: random
|
12 |
+
architecture: qwen
|
13 |
+
experts_per_token: 3
|
14 |
+
dtype: bfloat16
|
15 |
+
experts:
|
16 |
+
- source_model: Qwen/Qwen2.5-1.5B-Instruct
|
17 |
+
- source_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
18 |
+
- source_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
19 |
+
- source_model: huihui-ai/Qwen2.5-1.5B-Instruct-abliterated
|
20 |
+
- source_model: Rombo-Org/Rombo-LLM-V2.5-Qwen-1.5b
|
21 |
+
- source_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
22 |
+
- source_model: Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct
|
23 |
+
- source_model: RefalMachine/RuadaptQwen2.5-1.5B-instruct
|
24 |
+
shared_experts:
|
25 |
+
- source_model: Qwen/Qwen2.5-1.5B-Instruct
|
26 |
+
positive_prompts: [""]
|
27 |
+
residual_scale: 0.1
|
28 |
+
```
|