menglc
/

SliMM-DeepStackE-Qwen2VL-2B

Image-Text-to-Text

text2text-generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

menglc commited on Jan 4

Commit

30bb024

·

verified ·

1 Parent(s): 7345e93

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -97,8 +97,8 @@ print(output_text)
 |----------------------------------------------------------|------------|----------------|-------------|-------------|
 |Qwen2VL-2B (official evaluation)                          |41.1        | 73.5           |74.7         |90.1*         |
 |Qwen2VL-2B (our evaluation, 1024 max vistokens to LLM)    |39.4        | 75.6           |70.7         |90.4         |
-|SliMM-DeepStackE-Qwen2VL-0.5B (256 max vistokens to LLM)  |40.7        | 74.5           |74.7         |85.4         |
-|SliMM-DeepStackE-Qwen2VL-0.5B (400 max vistokens to LLM)  |41.2        | 76.8           |74.9         |88.0         |
  <code>*</code> indicates the performance on DocVQA test set

 |----------------------------------------------------------|------------|----------------|-------------|-------------|
 |Qwen2VL-2B (official evaluation)                          |41.1        | 73.5           |74.7         |90.1*         |
 |Qwen2VL-2B (our evaluation, 1024 max vistokens to LLM)    |39.4        | 75.6           |70.7         |90.4         |
+|SliMM-DeepStackE-Qwen2VL-2B (256 max vistokens to LLM)  |40.7        | 74.5           |74.7         |85.4         |
+|SliMM-DeepStackE-Qwen2VL-2B (400 max vistokens to LLM)  |41.2        | 76.8           |74.9         |88.0         |
  <code>*</code> indicates the performance on DocVQA test set