change model

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" or "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ"
+model_name = "TheBloke/Llama-2-7B-Chat-GGML" #"openai-community/gpt2" or "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ" or "TheBloke/Llama-2-7B-Chat-GGML" or "TheBloke/zephyr-7B-beta-GPTQ"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 #model = AutoModelForSeq2SeqLM.from_pretrained(model_name) 
 model = AutoModelForCausalLM.from_pretrained(model_name)
@@ -17,6 +17,11 @@ def generate_text(input_text):
     output = model.generate(input_ids, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2, top_k=50, top_p=0.95, temperature=0.7)
     return tokenizer.decode(output[0], skip_special_tokens=True)
 
+# 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_new_tokens=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
 # #model.save_pretrained("model")
 # #tokenizer.save_pretrained("model")