Hugging Face's logo

KE-Team
/
Ke-Omni-R-3B

Audio-Text-to-Text
Safetensors
English
Chinese
qwen2_5_omni_thinker
Model card Files
xet
Community
1
shuaijiang commited on
Commit
b6a1e81
·
verified ·
1 Parent(s): ce9bd55

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -34,9 +34,10 @@ Ke-Omni-R is an advanced audio reasoning model built upon [Qwen2.5-Omni-3B](http
34
  | Audio-Reasoner(Qwen2-Audio-7B-Instruct) | \[1\] | 60.06 | - | 64.30 | - | 60.70 | - | 61.71 | - |
35
  | Audio-Cot(Qwen2-Audio-7B-Instruct) | \[2\] | 61.86 | - | 56.29 | - | 55.26 | - | 57.80 | - |
36
  | R1-AQA(Qwen2-Audio-7B-Instruct) | \[3\] | 68.77 | 69.76 | 64.37 | 61.40 | 63.66 | 62.70 | 65.60 | 64.36 |
 
37
  | Qwen2.5-Omni-7B | \[4\] | 67.87 | - | 69.16 | - | 59.76 | - | 65.60 | - |
38
  | Ke-Omni-R-3B(Qwen2.5-Omni-3B) | GRPO(ours) | - | - | - | - |- | - | - |- |
39
- | Ke-Omni-R(Qwen2.5-Omni-7B) | GRPO(ours) | **69.37** | **71.90** | 69.46 | 67.13 |**67.87** | 67.10 | **68.90** |**68.71** |
40
 
41
  Note:
42
 
 
34
  | Audio-Reasoner(Qwen2-Audio-7B-Instruct) | \[1\] | 60.06 | - | 64.30 | - | 60.70 | - | 61.71 | - |
35
  | Audio-Cot(Qwen2-Audio-7B-Instruct) | \[2\] | 61.86 | - | 56.29 | - | 55.26 | - | 57.80 | - |
36
  | R1-AQA(Qwen2-Audio-7B-Instruct) | \[3\] | 68.77 | 69.76 | 64.37 | 61.40 | 63.66 | 62.70 | 65.60 | 64.36 |
37
+ | Qwen2.5-Omni-3B | \[4\] | **70.27** | - | 60.48 | - | 59.16 | - | 63.30 | - |
38
  | Qwen2.5-Omni-7B | \[4\] | 67.87 | - | 69.16 | - | 59.76 | - | 65.60 | - |
39
  | Ke-Omni-R-3B(Qwen2.5-Omni-3B) | GRPO(ours) | - | - | - | - |- | - | - |- |
40
+ | Ke-Omni-R(Qwen2.5-Omni-7B) | GRPO(ours) | 69.37 | **71.90** | 69.46 | 67.13 |**67.87** | 67.10 | **68.90** |**68.71** |
41
 
42
  Note:
43