lbourdois commited on
Commit
b55320b
·
verified ·
1 Parent(s): 65a426b

Improve language tag

Browse files

Hi! As the model is multilingual, this is a PR to add other languages than English to the language tag to improve the referencing. Note that 29 languages are announced in the README, but only 13 are explicitly listed. I was therefore only able to add these 13 languages.

Files changed (1) hide show
  1. README.md +30 -16
README.md CHANGED
@@ -1,17 +1,31 @@
1
- ---
2
- library_name: transformers
3
- datasets:
4
- - PowerInfer/QWQ-LONGCOT-500K
5
- - PowerInfer/LONGCOT-Refine-500K
6
- base_model:
7
- - Qwen/Qwen2.5-7B-Instruct
8
- license: apache-2.0
9
- ---
10
-
11
- # Qwen2.5-7B-Instruct-QwQ
12
-
13
- A QwQ style model trained from [Qwen/Qwen2.5-7B-Instruct](Qwen/Qwen2.5-7B-Instruct)
14
-
15
- - 1.7 epoch on [PowerInfer/QWQ-LONGCOT-500K](PowerInfer/QWQ-LONGCOT-500K) and [PowerInfer/LONGCOT-Refine-500K](PowerInfer/LONGCOT-Refine-500K)
16
- - recommended parameters: `temperature=0.7 top_p=0.8 repetition_penalty=1.1 max_tokens=16384`
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  - AIME24: 35.33% (average of 5 runs)
 
1
+ ---
2
+ library_name: transformers
3
+ datasets:
4
+ - PowerInfer/QWQ-LONGCOT-500K
5
+ - PowerInfer/LONGCOT-Refine-500K
6
+ base_model:
7
+ - Qwen/Qwen2.5-7B-Instruct
8
+ license: apache-2.0
9
+ language:
10
+ - zho
11
+ - eng
12
+ - fra
13
+ - spa
14
+ - por
15
+ - deu
16
+ - ita
17
+ - rus
18
+ - jpn
19
+ - kor
20
+ - vie
21
+ - tha
22
+ - ara
23
+ ---
24
+
25
+ # Qwen2.5-7B-Instruct-QwQ
26
+
27
+ A QwQ style model trained from [Qwen/Qwen2.5-7B-Instruct](Qwen/Qwen2.5-7B-Instruct)
28
+
29
+ - 1.7 epoch on [PowerInfer/QWQ-LONGCOT-500K](PowerInfer/QWQ-LONGCOT-500K) and [PowerInfer/LONGCOT-Refine-500K](PowerInfer/LONGCOT-Refine-500K)
30
+ - recommended parameters: `temperature=0.7 top_p=0.8 repetition_penalty=1.1 max_tokens=16384`
31
  - AIME24: 35.33% (average of 5 runs)