Add the "max_length" parameter to the Generation configuration.

The 12B model does not match the performance of the 1.2B model as the generation defaults to the max_length of "20". This results in shorter sequences than the model should be generating. For example on WMT14-DE-EN: the 12B model scores 15.52 and the 1.2B model scores 31.786 (SacreBLEU). The default max_length is properly set in the smaller models (see https://huggingface.co/facebook/m2m100_1.2B/blob/main/generation_config.json) and the 12B models should match this. I am submitting similar PRs for the other 12B models.

generation_config.json

@@ -2,6 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
+  "max_length": 200,
   "eos_token_id": 2,
   "pad_token_id": 1,
   "transformers_version": "4.27.0.dev0"