captainkyd commited on
Commit
72adf3e
β€’
1 Parent(s): e0e2048

Update app.py

Browse files

wasn't keeping my stupid quant config grrrrr

Files changed (1) hide show
  1. app.py +4 -13
app.py CHANGED
@@ -24,19 +24,10 @@ Answer the Question by exploring multiple reasoning paths as follows:
24
  - Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
25
  In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
26
  """
27
-
28
- model = AutoModelForCausalLM.from_pretrained(
29
- model_path,
30
- device_map="auto",
31
- trust_remote_code=True,
32
- quantization_config=quantization_config,
33
- )
34
-
35
- model = AutoModelForCausalLM.from_pretrained(
36
- model_path,
37
- device_map="auto",
38
- trust_remote_code=True,
39
- quantization_config=quantization_config,
40
  )
41
 
42
  model_path = "WhiteRabbitNeo/Trinity-13B"
 
24
  - Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
25
  In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
26
  """
27
+ quantization_config = BitsAndBytesConfig(
28
+ load_in_4bit=True,
29
+ bnb_4bit_use_double_quant=True,
30
+ bnb_4bit_compute_dtype=torch.bfloat16
 
 
 
 
 
 
 
 
 
31
  )
32
 
33
  model_path = "WhiteRabbitNeo/Trinity-13B"