OpenSourceRonin commited on
Commit
9da61be
1 Parent(s): cc040f7

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -4
app.py CHANGED
@@ -12,6 +12,14 @@ from huggingface_hub import snapshot_download
12
  from vptq.app_utils import get_chat_loop_generator
13
 
14
  models = [
 
 
 
 
 
 
 
 
15
  {
16
  "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft",
17
  "bits": "2 bits"
@@ -24,10 +32,6 @@ models = [
24
  "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-65536-woft",
25
  "bits": "4 bits"
26
  },
27
- {
28
- "name": "VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft",
29
- "bits": "4 bits"
30
- },
31
  {
32
  "name": "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-65536-woft",
33
  "bits": "4 bits"
 
12
  from vptq.app_utils import get_chat_loop_generator
13
 
14
  models = [
15
+ {
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"
 
32
  "name": "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-65536-woft",
33
  "bits": "4 bits"
34
  },
 
 
 
 
35
  {
36
  "name": "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-65536-woft",
37
  "bits": "4 bits"