ehristoforu commited on
Commit
884bcb6
·
verified ·
1 Parent(s): f233449

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -0
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
+ ```