Update app_v3.py

app_v3.py

@@ -1,9 +1,9 @@
-from transformers import AutoTokenizer, TextStreamer, pipeline, logging
+from transformers import AutoTokenizer, TextStreamer, pipeline
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 import time
 
-model_name_or_path = "TheBloke/llama2_7b_chat_uncensored-GPTQ"
-model_basename = "gptq_model-4bit-128g"
+model_name_or_path = "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ"
+model_basename = "Jackson2-gptq_model-4bit-128g"
 
 use_triton = False
 
@@ -17,17 +17,6 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         use_triton=use_triton,
         quantize_config=None)
 
-"""
-To download from a specific branch, use the revision parameter, as in this example:
-
-model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
-        revision="gptq-4bit-32g-actorder_True",
-        model_basename=model_basename,
-        use_safetensors=True,
-        trust_remote_code=True,
-        device="cuda:0",
-        quantize_config=None)
-"""
 
 prompt = "Tell me about AI"
 prompt_template=f'''### HUMAN: