Visual Question Answering
PEFT
Safetensors
French
English
SOKOUDJOU commited on
Commit
673d349
·
verified ·
1 Parent(s): 71128ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -7
README.md CHANGED
@@ -87,21 +87,18 @@ with torch.inference_mode():
87
 
88
  ### Results
89
 
90
- By following the **[LLM-as-Juries](https://arxiv.org/abs/2404.18796)** evaluation method, the following results were obtained using three judge models (GPT-4o, Gemini1.5 Pro and Claude 3.5-Sonnet). These models were evaluated based on the average of two criteria: response accuracy and completeness, similar to what the [SSA metric](https://arxiv.org/abs/2001.09977) aims to capture. This metric was adapted to the VQA context, with clear criteria for each score (0 to 5) to ensure the highest possible precision in meeting expectations.
91
 
92
- ![constellation](https://i.postimg.cc/kMRmcBpQ/constellation-0.png)
93
 
94
 
95
  ## Citation
96
 
97
  ```bibtex
98
- @online{Deidefics2,
99
  AUTHOR = {Loïc SOKOUDJOU SONAGU and Yoann SOLA},
100
  URL = {https://huggingface.co/cmarkea/idefics2-8b-ft-docvqa-lora},
101
  YEAR = {2024},
102
  KEYWORDS = {Multimodal ; VQA},
103
  }
104
- ```
105
- Find the base model paper [here](https://arxiv.org/pdf/2405.02246).
106
-
107
- - PEFT 0.11.1
 
87
 
88
  ### Results
89
 
90
+ By following the **[LLM-as-Juries](https://arxiv.org/abs/2404.18796)** evaluation method, the following results were obtained using three judge models (GPT-4o, Gemini1.5 Pro and Claude 3.5-Sonnet). This metric was adapted to the VQA context, with clear criteria for each score (0 to 5) to ensure the highest possible precision in meeting expectations.
91
 
92
+ ![constellation](https://i.postimg.cc/t4tjhy6b/constellation-0.png)
93
 
94
 
95
  ## Citation
96
 
97
  ```bibtex
98
+ @online{SOSoIdefics2,
99
  AUTHOR = {Loïc SOKOUDJOU SONAGU and Yoann SOLA},
100
  URL = {https://huggingface.co/cmarkea/idefics2-8b-ft-docvqa-lora},
101
  YEAR = {2024},
102
  KEYWORDS = {Multimodal ; VQA},
103
  }
104
+ ```