Update README.md

README.md

@@ -8,9 +8,9 @@ datasets:
 - twitter-api
 ---
 
-# Twitter June 2022 (RoBERTa-base, 154M)
+# Twitter September 2022 (RoBERTa-base, 169M)
 
-This is a RoBERTa-base model trained on 153.86M tweets until the end of June 2022 (15M tweets increment).
+This is a RoBERTa-base model trained on 168.86M tweets until the end of September 2022 (15M tweets increment).
 More details and performance scores are available in the [TimeLMs paper](https://arxiv.org/abs/2202.03829).
 
 Below, we provide some usage examples using the standard Transformers interface. For another interface more suited to comparing predictions and perplexity scores between models trained at different temporal intervals, check the [TimeLMs repository](https://github.com/cardiffnlp/timelms).
@@ -36,7 +36,7 @@ def preprocess(text):
 ```python
 from transformers import pipeline, AutoTokenizer
 
-MODEL = "cardiffnlp/twitter-roberta-base-jun2022-15M-incr"
+MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
 fill_mask = pipeline("fill-mask", model=MODEL, tokenizer=MODEL)
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
@@ -99,7 +99,7 @@ def get_embedding(text):  # naive approach for demonstration
   return np.mean(features[0], axis=0) 
 
 
-MODEL = "cardiffnlp/twitter-roberta-base-jun2022-15M-incr"
+MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModel.from_pretrained(MODEL)
 
@@ -136,7 +136,7 @@ Most similar to:  The book was awesome
 from transformers import AutoTokenizer, AutoModel, TFAutoModel
 import numpy as np
 
-MODEL = "cardiffnlp/twitter-roberta-base-jun2022-15M-incr"
+MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
 text = "Good night 😊"