Update app.py

app.py

@@ -17,7 +17,8 @@ models = ["Helsinki-NLP",
           "facebook/mbart-large-50-many-to-many-mmt",
           "utter-project/EuroLLM-1.7B",
           "Unbabel/TowerInstruct-7B-v0.2",
-          "Unbabel/TowerInstruct-Mistral-7B-v0.2"
+          "Unbabel/TowerInstruct-Mistral-7B-v0.2",
+          "openGPT-X/Teuken-7B-instruct-commercial-v0.4"
           ]
 
 def model_to_cuda(model):
@@ -29,6 +30,35 @@ def model_to_cuda(model):
         print("CUDA not available! Using CPU.")
     return model
 
+def teuken(model_name, sl, tl, input_text):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    # model_name = "openGPT-X/Teuken-7B-instruct-commercial-v0.4"
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        trust_remote_code=True,
+        torch_dtype=torch.bfloat16,
+    )
+    model = model.to(device).eval()
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_name,
+        use_fast=False,
+        trust_remote_code=True,
+    )
+    translation_prompt = f"Translate the following text from {sl} into {tl}: {input_text}"
+    messages = [{"role": "User", "content": translation_prompt}]
+    prompt_ids = tokenizer.apply_chat_template(messages, chat_template=sl.upper(), tokenize=True, add_generation_prompt=True, return_tensors="pt")
+    prediction = model.generate(
+        prompt_ids.to(model.device),
+        max_length=512,
+        do_sample=True,
+        top_k=50,
+        top_p=0.95,
+        temperature=0.7,
+        num_return_sequences=1,
+    )
+    prediction_text = tokenizer.decode(prediction[0].tolist())
+    return prediction_text
+
 def eurollm(model_name, sl, tl, input_text):
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name)  
@@ -67,6 +97,10 @@ def translate_text(input_text, sselected_language, tselected_language, model_nam
     if 'eurollm' in model_name.lower():
         translated_text = eurollm(model_name, sselected_language, tselected_language, input_text)
         return translated_text, message_text
+
+    if 'teuken' in model_name.lower():
+        translated_text = eurollm(model_name, sselected_language, tselected_language, input_text)
+        return translated_text, message_text
         
     if 'nllb' in model_name.lower():
         nnlbsl, nnlbtl = languagecodes.nllb_language_codes[sselected_language], languagecodes.nllb_language_codes[tselected_language]