Update README.md

README.md

@@ -20,7 +20,7 @@ This model is released as part of the project ["IT5: Large-Scale Text-to-Text Pr
 
 ## Model variants
 
-This repository contains the checkpoints for the `base` version of the model. The model was trained for one epoch (1.05M steps) on the [Thoroughly Cleaned Italian mC4 Corpus](https://huggingface.co/datasets/gsarti/clean_mc4_it) (~41B words, ~275GB) using 🤗 Datasets and the `google/t5-v1_1-base` improved configuration. Another version of this model trained on the [OSCAR corpus](https://oscar-corpus.com/) is also available under the name [`gsarti/it5-base-oscar`](https://huggingface.co/gsartiit5-base-oscar). The training procedure is made available [on Github](https://github.com/gsarti/t5-flax-gcp).
+This repository contains the checkpoints for the `base` version of the model. The model was trained for one epoch (1.05M steps) on the [Thoroughly Cleaned Italian mC4 Corpus](https://huggingface.co/datasets/gsarti/clean_mc4_it) (~41B words, ~275GB) using 🤗 Datasets and the `google/t5-v1_1-base` improved configuration. Another version of this model trained on the [OSCAR corpus](https://oscar-corpus.com/) is also available under the name [`gsarti/it5-base-oscar`](https://huggingface.co/gsartiit5-base-oscar). The training procedure is made available [on Github](https://github.com/gsarti/t5-flax-gcp).
 
 The following table summarizes the parameters for all available models
 
@@ -66,7 +66,7 @@ model_tf = TFT5ForConditionalGeneration.from_pretrained("gsarti/it5-base")
 
 ## Limitations
 
-Due to the nature of the web-scraped corpus on which IT5 models were trained, it likely that that their usage could reproduce and amplify pre-existing biases in the data, resulting in potentially harmful content such as racial or gender stereotypes and conspiracist views. For this reason, the study of such biases is explicitly encouraged, and model usage should ideally be restricted to research-oriented and non-user-facing endeavors.
+Due to the nature of the web-scraped corpus on which IT5 models were trained, it is likely that their usage could reproduce and amplify pre-existing biases in the data, resulting in potentially harmful content such as racial or gender stereotypes and conspiracist views. For this reason, the study of such biases is explicitly encouraged, and model usage should ideally be restricted to research-oriented and non-user-facing endeavors.
 
 ## Model curators