Update app.py

app.py

@@ -3,14 +3,22 @@ from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 from huggingface_hub import snapshot_download
 
-local_folder = "/workspace/model"
+import shutil
+import os
+
+cwd = os.getcwd()
+cachedir = cwd+'/cache'
+os.mkdir(cachedir)
+os.environ['HF_HOME'] = cachedir
+
+local_folder = cachedir + "/model"
 
 
 quantized_model_dir = "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ"
 
 snapshot_download(repo_id=quantized_model_dir, local_dir=local_folder, local_dir_use_symlinks=False)
 
-model_basename = "/model/Jackson2-4bit-128g-GPTQ.safetensors"
+model_basename = cachedir + "/model/Jackson2-4bit-128g-GPTQ.safetensors"
 
 use_strict = False