Update README.md

README.md

@@ -12,8 +12,12 @@ tags:
 metrics:
 - bleu
 widget:
-- text: "Je vais à la piscine avec ma maman aujourd'hui"
-example_title : "A simple sentence"
+- text: "je mange une pomme"
+  example_title: "A simple sentence"
+- text: "je ne pense pas à toi"
+  example_title: "Sentence with a negation"
+- text: "il y a 2 jours, les gendarmes ont vérifié ma licence"
+  example_title: "Sentence with a polylexical term"
 ---
 
 # t2p-t5-large-orféo
@@ -37,25 +41,19 @@ example_title : "A simple sentence"
 ## Using t2p-t5-large-orféo model with HuggingFace transformers
 
 ```python
-import torch
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-import numpy as np
 
 source_lang = "fr"
 target_lang = "frp"
 max_input_length = 128
 max_target_length = 128
 
-def load_model(checkpoint):
-    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-    model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
-    model = model.to("cuda:0")
-    return tokenizer, model
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
 
-def generate(sentence, tokenizer, model):
-    inputs = tokenizer("Je mange une pomme", return_tensors="pt").input_ids
-    outputs = model.generate(inputs.to("cuda:0"), max_new_tokens=40, do_sample=True, top_k=30, top_p=0.95)
-    pred = tokenizer.decode(outputs[0], skip_special_tokens=True)
+inputs = tokenizer("Je mange une pomme", return_tensors="pt").input_ids
+outputs = model.generate(inputs.to("cuda:0"), max_new_tokens=40, do_sample=True, top_k=30, top_p=0.95)
+pred = tokenizer.decode(outputs[0], skip_special_tokens=True)
 ```
 
 - **Language(s):** French