Hugging Face's logo

LiquidAI
/
LFM2-VL-450M

Image-Text-to-Text
Transformers
Safetensors
English
lfm2-vl
liquid
lfm2
edge
conversational
custom_code
Model card Files
xet
Community
2
liquidalex commited on
Commit
a04df42
·
verified ·
1 Parent(s): 688192d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -154,15 +154,15 @@ We recommend fine-tuning LFM2-VL models on your use cases to maximize performanc
154
 
155
  | Model | RealWorldQA | MM-IFEval | InfoVQA (Val) | OCRBench | BLINK | MMStar | MMMU (Val) | MathVista | SEEDBench_IMG | MMVet | MME | MMLU |
156
  |-------------------|-------------|-----------|---------------|----------|-------|--------|------------|-----------|---------------|-------|----------|-------|
157
- | InternVL3-2B | 65.10 | 38.49 | 66.10 | 831.00 | 53.10 | 61.10 | 48.70 | 57.60 | 75.00 | 67.00 | 2186.40 | 64.80 |
158
- | InternVL3-1B | 57.00 | 31.14 | 54.94 | 798.00 | 43.00 | 52.30 | 43.20 | 46.90 | 71.20 | 58.70 | 1912.40 | 49.80 |
159
- | SmolVLM2-2.2B | 57.50 | 19.42 | 37.75 | 725.00 | 42.30 | 46.00 | 41.60 | 51.50 | 71.30 | 34.90 | 1792.50 | - |
160
- | LFM2-VL-1.6B | 65.23 | 37.66 | 58.68 | 742.00 | 44.40 | 49.53 | 38.44 | 51.10 | 71.97 | 48.07 | 1753.04 | 50.99 |
161
 
162
  | Model | RealWorldQA | MM-IFEval | InfoVQA (Val) | OCRBench | BLINK | MMStar | MMMU (Val) | MathVista | SEEDBench_IMG | MMVet | MME | MMLU |
163
  |-------------------|-------------|-----------|---------------|----------|-------|--------|------------|-----------|---------------|-------|----------|-------|
164
- | SmolVLM2-500M | 49.90 | 11.27 | 24.64 | 609.00 | 40.70 | 38.20 | 34.10 | 37.50 | 62.20 | 29.90 | 1448.30 | - |
165
- | LFM2-VL-450M | 52.29 | 26.18 | 46.51 | 655.00 | 41.98 | 40.87 | 33.11 | 44.70 | 63.50 | 33.76 | 1239.06 | 40.16 |
166
 
167
  We obtained MM-IFEval and InfoVQA (Val) scores for InternVL 3 and SmolVLM2 models using VLMEvalKit.
168
 
 
154
 
155
  | Model | RealWorldQA | MM-IFEval | InfoVQA (Val) | OCRBench | BLINK | MMStar | MMMU (Val) | MathVista | SEEDBench_IMG | MMVet | MME | MMLU |
156
  |-------------------|-------------|-----------|---------------|----------|-------|--------|------------|-----------|---------------|-------|----------|-------|
157
+ | InternVL3-2B | 65.10 | 38.49 | 66.10 | 831 | 53.10 | 61.10 | 48.70 | 57.60 | 75.00 | 67.00 | 2186.40 | 64.80 |
158
+ | InternVL3-1B | 57.00 | 31.14 | 54.94 | 798 | 43.00 | 52.30 | 43.20 | 46.90 | 71.20 | 58.70 | 1912.40 | 49.80 |
159
+ | SmolVLM2-2.2B | 57.50 | 19.42 | 37.75 | 725 | 42.30 | 46.00 | 41.60 | 51.50 | 71.30 | 34.90 | 1792.50 | - |
160
+ | LFM2-VL-1.6B | 65.23 | 37.66 | 58.68 | 742 | 44.40 | 49.53 | 38.44 | 51.10 | 71.97 | 48.07 | 1753.04 | 50.99 |
161
 
162
  | Model | RealWorldQA | MM-IFEval | InfoVQA (Val) | OCRBench | BLINK | MMStar | MMMU (Val) | MathVista | SEEDBench_IMG | MMVet | MME | MMLU |
163
  |-------------------|-------------|-----------|---------------|----------|-------|--------|------------|-----------|---------------|-------|----------|-------|
164
+ | SmolVLM2-500M | 49.90 | 11.27 | 24.64 | 609 | 40.70 | 38.20 | 34.10 | 37.50 | 62.20 | 29.90 | 1448.30 | - |
165
+ | LFM2-VL-450M | 52.29 | 26.18 | 46.51 | 655 | 41.98 | 40.87 | 33.11 | 44.70 | 63.50 | 33.76 | 1239.06 | 40.16 |
166
 
167
  We obtained MM-IFEval and InfoVQA (Val) scores for InternVL 3 and SmolVLM2 models using VLMEvalKit.
168