Update README.md

Remove mention of MADLAD - did not bother benchmarking because it would not fit in GPU RAM on an RTX 4070s with 12 GB memory

README.md

@@ -74,7 +74,7 @@ The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so
 
 ## Metrics
 
-BLEU and CHRF2 calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores) ("zho_Hans"->"eng_Latn"). COMET22 with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate (using `ctranslate2`) the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32 except for `madlad400-3b-mt` which used a batch size of 1. 
+BLEU and CHRF2 calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores) ("zho_Hans"->"eng_Latn"). COMET22 with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate (using `ctranslate2`) the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32. 
 
 | Model                            | bleu  | chrf2 | comet22  | Time (s) |
 | -------------------------------- | ----- | ----- | ----     |  ----    |