Update app.py

app.py

@@ -5,9 +5,9 @@ import torch
 from peft import PeftConfig, PeftModel
 from transformers import LlamaForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
-config = PeftConfig.from_pretrained("GGmorello/FLAMES")
+# config = PeftConfig.from_pretrained("GGmorello/FLAMES")
 model = LlamaForCausalLM.from_pretrained(
-    config.base_model_name_or_path,
+    "GGmorello/FLAMES_100k",
     quantization_config=BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_quant_type="nf4",
@@ -15,7 +15,7 @@ model = LlamaForCausalLM.from_pretrained(
         bnb_4bit_compute_dtype=torch.bfloat16,
     ),
 )
-model = PeftModel.from_pretrained(model, "GGmorello/FLAMES")
+# model = PeftModel.from_pretrained(model, "GGmorello/FLAMES")
 
 
 MAX_SEQ_LEN = 4096