OpenSourceRonin commited on
Commit
a005089
·
verified ·
1 Parent(s): 0ec2418

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -13
app.py CHANGED
@@ -16,26 +16,14 @@ models = [
16
  "name": "VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-256-woft",
17
  "bits": "3 bits"
18
  },
19
- {
20
- "name": "VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft",
21
- "bits": "4 bits"
22
- },
23
  {
24
  "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft",
25
  "bits": "2 bits"
26
  },
27
- {
28
- "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-256-woft",
29
- "bits": "3 bits"
30
- },
31
  {
32
  "name": "VPTQ-community/Qwen2.5-72B-Instruct-v16-k65536-65536-woft",
33
  "bits": "2 bits"
34
- },
35
- {
36
- "name": "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-256-woft",
37
- "bits": "3 bits"
38
- },
39
  ]
40
 
41
  # Queues for storing historical data (saving the last 100 GPU utilization and memory usage values)
 
16
  "name": "VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-256-woft",
17
  "bits": "3 bits"
18
  },
 
 
 
 
19
  {
20
  "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft",
21
  "bits": "2 bits"
22
  },
 
 
 
 
23
  {
24
  "name": "VPTQ-community/Qwen2.5-72B-Instruct-v16-k65536-65536-woft",
25
  "bits": "2 bits"
26
+ }
 
 
 
 
27
  ]
28
 
29
  # Queues for storing historical data (saving the last 100 GPU utilization and memory usage values)