Update README.md

README.md

@@ -7,9 +7,9 @@ tags:
 - Optimum-Intel
 ---
 
-`Nanonets-OCR2-3B` is based on `Qwen2.5-VL-3B`, which ususally performs when quantization approaches keep vision encoder in full precision.
-My usecase involves dense table extraction; for now, I'll hypothesize Nanonet finetuning takes "pressure" off the language model component. 
-To test this, I used instructions using instructions which do not deviate so much from training data. 
+`Nanonets-OCR2-3B` is based on `Qwen2.5-VL-3B`, which ususally performs better when quantization approaches keep the vision encoder in full precision.
+My usecase involves dense table extraction; for now, I'll hypothesize Nanonet finetuning takes "pressure" off the language model component so keeping vision encoder in higher precision retains more understanding of vision tokens, which represent information differently than text tokens. 
+To test this, I used instructions which do not deviate so much from training data, which Nanonets reccomends in their examples. 
 
 Based on the Qwen-VL papers, this behavior may echo QwenTeam training recipie for ViT and LLM components, where each part was trained seperately, then ViT was frozen, the language model was merged.