Update config.json
#1
by
IlyasMoutawwakil
HF Staff
- opened
- config.json +1 -69
config.json
CHANGED
@@ -11,40 +11,6 @@
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 32,
|
13 |
"layer_types": [
|
14 |
-
"full_attention",
|
15 |
-
"full_attention",
|
16 |
-
"full_attention",
|
17 |
-
"full_attention",
|
18 |
-
"full_attention",
|
19 |
-
"full_attention",
|
20 |
-
"full_attention",
|
21 |
-
"full_attention",
|
22 |
-
"full_attention",
|
23 |
-
"full_attention",
|
24 |
-
"full_attention",
|
25 |
-
"full_attention",
|
26 |
-
"full_attention",
|
27 |
-
"full_attention",
|
28 |
-
"full_attention",
|
29 |
-
"full_attention",
|
30 |
-
"full_attention",
|
31 |
-
"full_attention",
|
32 |
-
"full_attention",
|
33 |
-
"full_attention",
|
34 |
-
"full_attention",
|
35 |
-
"full_attention",
|
36 |
-
"full_attention",
|
37 |
-
"full_attention",
|
38 |
-
"full_attention",
|
39 |
-
"full_attention",
|
40 |
-
"full_attention",
|
41 |
-
"full_attention",
|
42 |
-
"full_attention",
|
43 |
-
"full_attention",
|
44 |
-
"full_attention",
|
45 |
-
"full_attention",
|
46 |
-
"full_attention",
|
47 |
-
"full_attention",
|
48 |
"full_attention",
|
49 |
"full_attention"
|
50 |
],
|
@@ -55,41 +21,7 @@
|
|
55 |
"no_rope_layer_interval": 4,
|
56 |
"no_rope_layers": [
|
57 |
1,
|
58 |
-
1
|
59 |
-
1,
|
60 |
-
0,
|
61 |
-
1,
|
62 |
-
1,
|
63 |
-
1,
|
64 |
-
0,
|
65 |
-
1,
|
66 |
-
1,
|
67 |
-
1,
|
68 |
-
0,
|
69 |
-
1,
|
70 |
-
1,
|
71 |
-
1,
|
72 |
-
0,
|
73 |
-
1,
|
74 |
-
1,
|
75 |
-
1,
|
76 |
-
0,
|
77 |
-
1,
|
78 |
-
1,
|
79 |
-
1,
|
80 |
-
0,
|
81 |
-
1,
|
82 |
-
1,
|
83 |
-
1,
|
84 |
-
0,
|
85 |
-
1,
|
86 |
-
1,
|
87 |
-
1,
|
88 |
-
0,
|
89 |
-
1,
|
90 |
-
1,
|
91 |
-
1,
|
92 |
-
0
|
93 |
],
|
94 |
"num_attention_heads": 4,
|
95 |
"num_hidden_layers": 2,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 32,
|
13 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"full_attention",
|
15 |
"full_attention"
|
16 |
],
|
|
|
21 |
"no_rope_layer_interval": 4,
|
22 |
"no_rope_layers": [
|
23 |
1,
|
24 |
+
1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
],
|
26 |
"num_attention_heads": 4,
|
27 |
"num_hidden_layers": 2,
|