anocha-mcomp commited on
Commit
05fdb29
·
verified ·
1 Parent(s): e12b260

Update model card from Confluence: Model Card: Gemma-SEA-LION-v4-4B-VL

Browse files
model_card_gemma-sea-lion-v4-4b-vl.md CHANGED
@@ -9,7 +9,7 @@ SEA-LION is a collection of Large Language Models (LLMs) which have been pretrai
9
  Gemma-SEA-LION-v4-4B-VL inherits the image and text capabilities from gemma-3-4b-it alongside its large context length of 128K tokens. Additionally, beyond extending the multilingual capabilities of the original gemma model for SEA languages, we experimented with:
10
 
11
  1. Adding function calling to the model to allow for this model to be used in tool calling applications
12
- 2. The OCR capabilities in Thai, Chinese and English
13
 
14
  ## Model Details
15
 
@@ -181,13 +181,13 @@ The evaluation was done using the codes from the BFCL v4 repository. Modificatio
181
 
182
  #### Results
183
 
184
- ### OCR
185
 
186
- We also evaluated the OCR capabilities using the components of the OCRBenchv2 and ThaiOCRBench that focused primarily on text extraction. These included the following tasks:
187
 
188
  - Table/Chart/Document parsing
189
- - Fine grained OCR
190
- - Full page OCR
191
  - Text recognition
192
 
193
  #### Factors
 
9
  Gemma-SEA-LION-v4-4B-VL inherits the image and text capabilities from gemma-3-4b-it alongside its large context length of 128K tokens. Additionally, beyond extending the multilingual capabilities of the original gemma model for SEA languages, we experimented with:
10
 
11
  1. Adding function calling to the model to allow for this model to be used in tool calling applications
12
+ 2. The visual parsing capabilities in Thai, Chinese and English
13
 
14
  ## Model Details
15
 
 
181
 
182
  #### Results
183
 
184
+ ### Visual parsing
185
 
186
+ We also evaluated the visual parsing capabilities using the components of the OCRBenchv2 and ThaiOCRBench that focused primarily on text extraction. These included the following tasks:
187
 
188
  - Table/Chart/Document parsing
189
+ - Fine grained image-text extraction
190
+ - Full page image-text extraction
191
  - Text recognition
192
 
193
  #### Factors