Hugging Face's logo

OpenSearch-AI
/
Ops-MM-embedding-v1-2B

Feature Extraction
Safetensors
multilingual
qwen2_vl
mmeb
multimodal-embedding
Model card Files
xet
Community
11
frozenc commited on
Commit
26d80df
·
verified ·
1 Parent(s): 6bfce3d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -38,11 +38,12 @@ MMEB-train, CC-3M, colpali training set.
38
 
39
  | Model | Model Size (B) | Overall | Image-Overall | Video-Overall | Visdoc-Overall |
40
  | ------------------------ | -------------- | ------- | ------------- | ------------- | -------------- |
41
- | seed-1.6-embedding | unknown | 71.57 | 77.78 | 55.34 | 74.41 |
42
- | Ops-MM-embedding-v1-7B | 8.29 | 67.79 | 72.72 | 53.76 | 70.91 |
43
- | Ops-MM-embedding-v1-2B | 2.21 | 63.62 | 69.03 | 47.56 | 67.55 |
44
- | VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.39 | 64.85 | 34.85 | 66.34 |
45
- | gme-Qwen2-VL-2B-Instruct | 2.21 | 54.37 | 51.89 | 33.86 | 73.47 |
 
46
 
47
 
48
  ### MMEB-Image
@@ -58,14 +59,13 @@ The table below compares performance on MMEB-Image benchmark among models of sim
58
 
59
  ### ViDoRe-v2
60
 
61
- | Model | Avg | ESG Restaurant Human | MIT Bio | Econ. Macro | ESG Restaurant Synth. | MIT Bio Multi. | Econ Macro Multi. | ESG Restaurant Synth. Multi. |
62
- | ---------------------- | -------- | -------------------- | ------- | ----------- | --------------------- | -------------- | ----------------- | ---------------------------- |
63
- | gme-7B | 59.3 | 65.8 | 64 | 62.9 | 54.3 | 55.1 | 56.2 | 56.7 |
64
- | seed 1.6 embedding | 58.9 | 63.3 | 63.9 | 64.0 | 58.4 | 57.1 | 53.8 | 52.0 |
65
- | Ops-MM-embedding-v1-7B | **60.6** | 66.3 | 58.4 | 67.4 | 60.0 | 54.3 | 60.9 | 56.8 |
66
- | Ops-MM-embedding-v1-2B | 54.4 | 58.6 | 56.0 | 56.4 | 55.8 | 52.9 | 47.9 | 53.4 |
67
-
68
 
 
 
 
 
 
 
69
 
70
 
71
  ## Usage
 
38
 
39
  | Model | Model Size (B) | Overall | Image-Overall | Video-Overall | Visdoc-Overall |
40
  | ------------------------ | -------------- | ------- | ------------- | ------------- | -------------- |
41
+ | seed-1.6-embedding | unknown | 71.27 | 77.78 | 55.34 | 73.44 |
42
+ | Ops-MM-embedding-v1-7B | 8.29 | 67.61 | 72.72 | 53.76 | 70.34 |
43
+ | Ops-MM-embedding-v1-2B | 2.21 | 63.44 | 69.03 | 47.56 | 66.96 |
44
+ | VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.02 | 64.85 | 34.85 | 65.36 |
45
+ | gme-Qwen2-VL-7B-Instruct | 8.29 | 57.83 | 55.95 | 38.43 | 75.18 |
46
+ | gme-Qwen2-VL-2B-Instruct | 2.21 | 54.08 | 51.89 | 33.64 | 72.71 |
47
 
48
 
49
  ### MMEB-Image
 
59
 
60
  ### ViDoRe-v2
61
 
 
 
 
 
 
 
 
62
 
63
+ | Model | Avg | ESG Restaurant Human | MIT Bio Multi. | Econ Macro Multi. | ESG Restaurant Synth. Multi. |
64
+ | ---------------------- | --------- | -------------------- | -------------- | ----------------- | ---------------------------- |
65
+ | gme-7B | 55.61 | 63.37 | 49.49 | 54.21 | 55.38 |
66
+ | seed 1.6 embedding | 56.57 | 63.3 | 57.14 | 53.85 | 51.99 |
67
+ | Ops-MM-embedding-v1-7B | **59.59** | 66.27 | 54.34 | 60.92 | 56.82 |
68
+ | Ops-MM-embedding-v1-2B | 53.18 | 58.57 | 52.87 | 47.89 | 53.39 |
69
 
70
 
71
  ## Usage