:books: fix typo in README

README.md

@@ -2,7 +2,7 @@
 language: 
 - fr
 
-thumbnail: https://github.com/AntoineSimoulin/gpt-fr/blob/main/imgs/logo.png?raw=true
+thumbnail: https://raw.githubusercontent.com/AntoineSimoulin/gpt-fr/main/imgs/logo.png
 tags:
 - tf
 - pytorch
@@ -22,7 +22,7 @@ license: apache-2.0
 | Model name | Number of layers | Attention Heads | Embedding Dimension | Total Parameters |
 | :------:       |   :---: | :---: | :---: | :---: |
 | `gpt-fr-cased-small` | 12    | 12    | 768   | 124 M |
-| `gpt-fr-cased-base` | 24    | 14    | 1,792   | 1,017 B |
+| `gpt-fr-cased-base` | 24    | 14    | 1792   | 1,017 B |
 
 ## Intended uses & limitations
 
@@ -46,10 +46,9 @@ input_ids = tokenizer.encode(input_sentence, return_tensors='pt')
 
 beam_outputs = model.generate(
     input_ids, 
-    max_length=200, 
+    max_length=100, 
     do_sample=True,   
     top_k=50, 
-    max_length=100,
     top_p=0.95, 
     num_return_sequences=1
 )
@@ -83,8 +82,11 @@ In line with the [WikiText](https://blog.einstein.ai/the-wikitext-long-term-depe
 ### BibTeX entry and citation info
 
 ```bibtex
-@inproceedings{...,
-  year={2020}
+@inproceedings{simoulin_2020_gptfr,
+  title         = {Un modèle Transformer Génératif Pré-entraîné pour le ______ français},
+  author        = {Simoulin, Antoine and Crabbé, Benoit},
+  year          = {2021},
+  pubstate      = {forthcoming},
 }
 ```