Daemontatox commited on
Commit
d83f798
1 Parent(s): 5a2fbc2

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -4
app.py CHANGED
@@ -59,9 +59,9 @@ h3 {
59
  device = "cuda" # for GPU usage or "cpu" for CPU usage
60
 
61
  quantization_config = BitsAndBytesConfig(
62
- load_in_8bit=True, # Use 8-bit instead of 4-bit
63
- bnb_8bit_compute_dtype=torch.bfloat16, # bfloat16 for compute
64
- bnb_8bit_use_double_quant=True # Disable double quantization
65
  )
66
 
67
  tokenizer = AutoTokenizer.from_pretrained(MODEL)
@@ -166,7 +166,8 @@ chatbot = gr.Chatbot(
166
  show_copy_button=True
167
  )
168
 
169
- DEFAULT_SYSTEM_PROMPT = """You are an AI expert at providing high-quality answers. Your process involves these steps:
 
170
  1. Initial Thought: Use the <Thinking> tag to reason step-by-step and generate your best possible response to the following request: [User's Request Here].
171
  Example:
172
  <Thinking>
 
59
  device = "cuda" # for GPU usage or "cpu" for CPU usage
60
 
61
  quantization_config = BitsAndBytesConfig(
62
+ load_in_4bit=True, # Use 8-bit instead of 4-bit
63
+ bnb_4bit_compute_dtype=torch.bfloat16, # bfloat16 for compute
64
+ bnb_4bit_use_double_quant=True # Disable double quantization
65
  )
66
 
67
  tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
166
  show_copy_button=True
167
  )
168
 
169
+ DEFAULT_SYSTEM_PROMPT = """You are a Sentient Reasoning AI , expert at providing high-quality answers.
170
+ Your process involves these steps:
171
  1. Initial Thought: Use the <Thinking> tag to reason step-by-step and generate your best possible response to the following request: [User's Request Here].
172
  Example:
173
  <Thinking>