smalll fixes

README.md

@@ -207,7 +207,7 @@ We start from the base IDEFICS models and fine-tune the models by unfreezing all
 
 We note that all these datasets were obtained by using ChatGPT/GPT-4 in one way or another.
 
-Additionally, we found it beneficial to include the pre-training data in the fine-tuning with the following sampling ratios: 5.1% of image-text pairs and 31.0 of multimodal web documents.
+Additionally, we found it beneficial to include the pre-training data in the fine-tuning with the following sampling ratios: 5.1% of image-text pairs and 30.7% of OBELICS multimodal web documents.
 
 The training objective is the standard next token prediction. We use the following hyper and training parameters:
 | Parameters | | IDEFICS-80b-instruct | IDEFICS-9b-instruct |
@@ -229,7 +229,7 @@ The training objective is the standard next token prediction. We use the followi
 
 # Evaluation
 
-## IDEFICS base
+## IDEFICS
 
 We follow the evaluation protocol of Flamingo and evaluate IDEFICS on a suite of downstream image-text benchmarks ranging from visual question answering to image captioning.