Update app.py

app.py

@@ -8,14 +8,12 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 DESCRIPTION = """\
-# Gemma 2 2B Neogenesis ITA 💎🌍🇮🇹
+# Gemma 2 9B Neogenesis ITA 💎🌍🇮🇹
 
-Fine-tuned version of Google/gemma-2-2b-it to improve the performance on the Italian language.
-Small (2.6 B parameters) but good model, with 8k context length.
+Fine-tuned version of VAGOsolutions/SauerkrautLM-gemma-2-9b-it to improve the performance on the Italian language.
+Good model with 9.24 billion parameters, with 8k context length.
 
-[🪪 **Model card**](https://huggingface.co/anakin87/gemma-2-2b-neogenesis-ita)
-
-[📓 **Kaggle notebook**](https://www.kaggle.com/code/anakin87/post-training-gemma-for-italian-and-beyond) - Learn how this model was trained.
+[🪪 **Model card**](https://huggingface.co/anakin87/gemma-2-9b-neogenesis-ita)
 """
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -24,7 +22,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "anakin87/gemma-2-2b-neogenesis-ita"
+model_id = "anakin87/gemma-2-9b-neogenesis-ita"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,