change max_length

app.py

@@ -6,7 +6,7 @@ import gradio as gr
 logger = logging.get_logger("transformers")
 
 # Load the model and tokenizer
-model_name = "TheBloke/zephyr-7B-beta-GPTQ" #"openai-community/gpt2"
+model_name = "TheBloke/zephyr-7B-beta-GPTQ" #"openai-community/gpt2" or "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 #model = AutoModelForSeq2SeqLM.from_pretrained(model_name) 
 model = AutoModelForCausalLM.from_pretrained(model_name)
@@ -14,7 +14,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 # Fonction pour générer du texte
 def generate_text(prompt):
     inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512, padding="max_length")
-    summary_ids = model.generate(inputs["input_ids"], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
+    summary_ids = model.generate(inputs["input_ids"], max_length=512, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
     return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
 # #for training the model after the data is collected