Shubhra Pandit commited on
Commit
4966942
·
1 Parent(s): 7e2a08d

Update model files - no router quantization, actorder static

Browse files
config.json CHANGED
@@ -32,7 +32,7 @@
32
  "Linear"
33
  ],
34
  "weights": {
35
- "actorder": "group",
36
  "block_structure": null,
37
  "dynamic": false,
38
  "group_size": 128,
@@ -46,8 +46,40 @@
46
  }
47
  },
48
  "format": "pack-quantized",
49
- "global_compression_ratio": 1.588184730583041,
50
  "ignore": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  "lm_head"
52
  ],
53
  "kv_cache_scheme": null,
 
32
  "Linear"
33
  ],
34
  "weights": {
35
+ "actorder": "weight",
36
  "block_structure": null,
37
  "dynamic": false,
38
  "group_size": 128,
 
46
  }
47
  },
48
  "format": "pack-quantized",
49
+ "global_compression_ratio": 1.4210061815911108,
50
  "ignore": [
51
+ "model.layers.0.block_sparse_moe.router.layer",
52
+ "model.layers.1.block_sparse_moe.router.layer",
53
+ "model.layers.2.block_sparse_moe.router.layer",
54
+ "model.layers.3.block_sparse_moe.router.layer",
55
+ "model.layers.4.block_sparse_moe.router.layer",
56
+ "model.layers.5.block_sparse_moe.router.layer",
57
+ "model.layers.6.block_sparse_moe.router.layer",
58
+ "model.layers.7.block_sparse_moe.router.layer",
59
+ "model.layers.8.block_sparse_moe.router.layer",
60
+ "model.layers.9.block_sparse_moe.router.layer",
61
+ "model.layers.10.block_sparse_moe.router.layer",
62
+ "model.layers.11.block_sparse_moe.router.layer",
63
+ "model.layers.12.block_sparse_moe.router.layer",
64
+ "model.layers.13.block_sparse_moe.router.layer",
65
+ "model.layers.14.block_sparse_moe.router.layer",
66
+ "model.layers.15.block_sparse_moe.router.layer",
67
+ "model.layers.16.block_sparse_moe.router.layer",
68
+ "model.layers.17.block_sparse_moe.router.layer",
69
+ "model.layers.18.block_sparse_moe.router.layer",
70
+ "model.layers.19.block_sparse_moe.router.layer",
71
+ "model.layers.20.block_sparse_moe.router.layer",
72
+ "model.layers.21.block_sparse_moe.router.layer",
73
+ "model.layers.22.block_sparse_moe.router.layer",
74
+ "model.layers.23.block_sparse_moe.router.layer",
75
+ "model.layers.24.block_sparse_moe.router.layer",
76
+ "model.layers.25.block_sparse_moe.router.layer",
77
+ "model.layers.26.block_sparse_moe.router.layer",
78
+ "model.layers.27.block_sparse_moe.router.layer",
79
+ "model.layers.28.block_sparse_moe.router.layer",
80
+ "model.layers.29.block_sparse_moe.router.layer",
81
+ "model.layers.30.block_sparse_moe.router.layer",
82
+ "model.layers.31.block_sparse_moe.router.layer",
83
  "lm_head"
84
  ],
85
  "kv_cache_scheme": null,
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c49b74fad37eac8a2b8019ec2994606e6d544a268a277e7930c68e1651e9ce6e
3
- size 4955753544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f4774e35b31bee0c4ddd2477f8b25d903a22d4352a12d806c4d027e273b12f
3
+ size 4957219408
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19358b682f3d85d5d2aa292ee20db7cb4677db4397e64824fdef3536530e2d65
3
- size 1492150912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7a0188031319a1d2e1ae9cf1fde9a63b28934c15adac29799a75ca1eb7bdd9
3
+ size 1492593440
model.safetensors.index.json CHANGED
@@ -1,775 +1,551 @@
1
  {
2
  "metadata": {
3
- "total_size": 6447814144
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00002-of-00002.safetensors",
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
  "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
9
  "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
11
- "model.layers.0.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
12
- "model.layers.0.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
13
- "model.layers.0.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
14
  "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
  "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
17
  "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
18
  "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
19
  "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
20
- "model.layers.0.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
21
  "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
22
  "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
23
  "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
24
- "model.layers.0.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
25
  "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
26
  "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
27
  "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
28
- "model.layers.0.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
29
  "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
30
  "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
31
  "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
32
  "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
33
  "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.1.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
35
- "model.layers.1.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
36
- "model.layers.1.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
37
- "model.layers.1.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
38
  "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.1.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
41
  "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
42
  "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
43
  "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
44
- "model.layers.1.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
45
  "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
46
  "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
47
  "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
48
- "model.layers.1.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
49
  "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
50
  "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
51
  "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
52
- "model.layers.1.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
53
  "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
54
  "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
55
  "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
56
  "model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
57
  "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.10.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
59
- "model.layers.10.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
60
- "model.layers.10.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
61
- "model.layers.10.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
62
  "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
  "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.10.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
65
  "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
66
  "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
67
  "model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
68
- "model.layers.10.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
69
  "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
70
  "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
71
  "model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
72
- "model.layers.10.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
73
  "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
74
  "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
75
  "model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
76
- "model.layers.10.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
77
  "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
78
  "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
79
  "model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
80
  "model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
81
  "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.11.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
83
- "model.layers.11.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
84
- "model.layers.11.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
85
- "model.layers.11.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
86
  "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
  "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.11.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
89
  "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
90
  "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
91
  "model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
92
- "model.layers.11.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
93
  "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
94
  "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
95
  "model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
96
- "model.layers.11.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
97
  "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
98
  "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
99
  "model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
100
- "model.layers.11.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
101
  "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
102
  "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
103
  "model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
104
  "model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
105
  "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.12.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
107
- "model.layers.12.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
108
- "model.layers.12.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
109
- "model.layers.12.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
110
  "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
  "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.12.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
113
  "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
114
  "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
115
  "model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
116
- "model.layers.12.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
117
  "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
118
  "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
119
  "model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
120
- "model.layers.12.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
121
  "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
122
  "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
123
  "model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
124
- "model.layers.12.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
125
  "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
126
  "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
127
  "model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
128
  "model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
129
  "model.layers.13.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.13.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
131
- "model.layers.13.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
132
- "model.layers.13.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
133
- "model.layers.13.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
134
  "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
  "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.13.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
137
  "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
138
  "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
139
  "model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
140
- "model.layers.13.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
141
  "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
142
  "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
143
  "model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
144
- "model.layers.13.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
145
  "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
146
  "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
147
  "model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
148
- "model.layers.13.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
149
  "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
150
  "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
151
  "model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
152
  "model.layers.14.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
153
  "model.layers.14.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
154
- "model.layers.14.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
155
- "model.layers.14.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
156
- "model.layers.14.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
157
- "model.layers.14.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
158
  "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
159
  "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.14.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
161
  "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
162
  "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
163
  "model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
164
- "model.layers.14.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
165
  "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
166
  "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
167
  "model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
168
- "model.layers.14.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
169
  "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
170
  "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
171
  "model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
172
- "model.layers.14.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
173
  "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
174
  "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
175
  "model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
176
  "model.layers.15.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
177
  "model.layers.15.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.15.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
179
- "model.layers.15.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
180
- "model.layers.15.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
181
- "model.layers.15.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
182
  "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
  "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.15.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
185
  "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
186
  "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
187
  "model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
188
- "model.layers.15.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
189
  "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
190
  "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
191
  "model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
192
- "model.layers.15.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
193
  "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
194
  "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
195
  "model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
196
- "model.layers.15.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
197
  "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
198
  "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
199
  "model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
200
  "model.layers.16.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
201
  "model.layers.16.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
202
- "model.layers.16.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
203
- "model.layers.16.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
204
- "model.layers.16.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
205
- "model.layers.16.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
206
  "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
  "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.16.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
209
  "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
210
  "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
211
  "model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
212
- "model.layers.16.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
213
  "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
214
  "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
215
  "model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
216
- "model.layers.16.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
217
  "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
218
  "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
219
  "model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
220
- "model.layers.16.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
221
  "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
222
  "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
223
  "model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
224
  "model.layers.17.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
225
  "model.layers.17.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.17.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
227
- "model.layers.17.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
228
- "model.layers.17.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
229
- "model.layers.17.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
230
  "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
231
  "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.17.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
233
  "model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
234
  "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
235
  "model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
236
- "model.layers.17.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
237
  "model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
238
  "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
239
  "model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
240
- "model.layers.17.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
241
  "model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
242
  "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
243
  "model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
244
- "model.layers.17.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
245
  "model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
246
  "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
247
  "model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
248
  "model.layers.18.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
249
  "model.layers.18.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.18.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
251
- "model.layers.18.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
252
- "model.layers.18.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
253
- "model.layers.18.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
254
  "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
255
  "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.18.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
257
  "model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
258
  "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
259
  "model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
260
- "model.layers.18.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
261
  "model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
262
  "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
263
  "model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
264
- "model.layers.18.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
265
  "model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
266
  "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
267
  "model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
268
- "model.layers.18.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
269
  "model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
270
  "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
271
  "model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
272
  "model.layers.19.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
273
  "model.layers.19.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
274
- "model.layers.19.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
275
- "model.layers.19.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
276
- "model.layers.19.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
277
- "model.layers.19.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
278
  "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
  "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.19.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
281
  "model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
282
  "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
283
  "model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
284
- "model.layers.19.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
285
  "model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
286
  "model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
287
  "model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
288
- "model.layers.19.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
289
  "model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
290
  "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
291
  "model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
292
- "model.layers.19.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
293
  "model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
294
  "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
295
  "model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
296
  "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
297
  "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
298
- "model.layers.2.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
299
- "model.layers.2.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
300
- "model.layers.2.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
301
- "model.layers.2.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
302
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
303
  "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
304
- "model.layers.2.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
305
  "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
306
  "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
307
  "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
308
- "model.layers.2.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
309
  "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
310
  "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
311
  "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
312
- "model.layers.2.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
313
  "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
314
  "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
315
  "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
316
- "model.layers.2.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
317
  "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
318
  "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
319
  "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
320
  "model.layers.20.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
321
  "model.layers.20.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
322
- "model.layers.20.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
323
- "model.layers.20.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
324
- "model.layers.20.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
325
- "model.layers.20.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
326
  "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
327
  "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
328
- "model.layers.20.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
329
  "model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
330
  "model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
331
  "model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
332
- "model.layers.20.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
333
  "model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
334
  "model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
335
  "model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
336
- "model.layers.20.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
337
  "model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
338
  "model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
339
  "model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
340
- "model.layers.20.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
341
  "model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
342
  "model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
343
  "model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
344
  "model.layers.21.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
345
  "model.layers.21.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
346
- "model.layers.21.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
347
- "model.layers.21.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
348
- "model.layers.21.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
349
- "model.layers.21.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
350
  "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
  "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
352
- "model.layers.21.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
353
  "model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
354
  "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
355
  "model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
356
- "model.layers.21.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
357
  "model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
358
  "model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
359
  "model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
360
- "model.layers.21.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
361
  "model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
362
  "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
363
  "model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
364
- "model.layers.21.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
365
  "model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
366
  "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
367
  "model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
368
  "model.layers.22.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
369
  "model.layers.22.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
370
- "model.layers.22.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
371
- "model.layers.22.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
372
- "model.layers.22.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
373
- "model.layers.22.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
374
  "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
375
  "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
- "model.layers.22.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
377
  "model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
378
  "model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
379
  "model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
380
- "model.layers.22.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
381
  "model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
382
  "model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
383
  "model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
384
- "model.layers.22.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
385
  "model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
386
  "model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
387
  "model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
388
- "model.layers.22.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
389
  "model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
390
  "model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
391
  "model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
392
  "model.layers.23.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
393
  "model.layers.23.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
394
- "model.layers.23.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
395
- "model.layers.23.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
396
- "model.layers.23.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
397
- "model.layers.23.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
398
  "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
  "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
400
- "model.layers.23.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
401
  "model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
402
  "model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
403
  "model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
404
- "model.layers.23.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
405
  "model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
406
  "model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
407
  "model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
408
- "model.layers.23.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
409
  "model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
410
  "model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
411
  "model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
412
- "model.layers.23.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
413
  "model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
414
  "model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
415
  "model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
416
  "model.layers.24.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
417
  "model.layers.24.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
418
- "model.layers.24.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
419
- "model.layers.24.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
420
- "model.layers.24.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
421
- "model.layers.24.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
422
  "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
423
  "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
424
- "model.layers.24.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
425
  "model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
426
  "model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
427
  "model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
428
- "model.layers.24.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
429
  "model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
430
  "model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
431
  "model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
432
- "model.layers.24.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
433
  "model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
434
  "model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
435
  "model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
436
- "model.layers.24.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
437
  "model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
438
  "model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
439
  "model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
440
  "model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
441
  "model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
442
- "model.layers.25.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
443
- "model.layers.25.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
444
- "model.layers.25.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
445
- "model.layers.25.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
446
  "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
447
  "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
448
- "model.layers.25.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
449
  "model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
450
  "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
451
  "model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
452
- "model.layers.25.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
453
  "model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
454
  "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
455
  "model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
456
- "model.layers.25.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
457
  "model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
458
  "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
459
  "model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
460
- "model.layers.25.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
461
  "model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
462
  "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
463
  "model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
464
  "model.layers.26.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
465
  "model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
466
- "model.layers.26.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
467
- "model.layers.26.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
468
- "model.layers.26.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
469
- "model.layers.26.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
470
  "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
471
  "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
472
- "model.layers.26.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
473
  "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
474
  "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
475
  "model.layers.26.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
476
- "model.layers.26.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
477
  "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
478
  "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
479
  "model.layers.26.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
480
- "model.layers.26.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
481
  "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
482
  "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
483
  "model.layers.26.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
484
- "model.layers.26.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
485
  "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
486
  "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
487
  "model.layers.26.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
488
  "model.layers.27.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
489
  "model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
490
- "model.layers.27.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
491
- "model.layers.27.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
492
- "model.layers.27.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
493
- "model.layers.27.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
494
  "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
495
  "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
496
- "model.layers.27.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
497
  "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
498
  "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
499
  "model.layers.27.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
500
- "model.layers.27.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
501
  "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
502
  "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
503
  "model.layers.27.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
504
- "model.layers.27.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
505
  "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
506
  "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
507
  "model.layers.27.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
508
- "model.layers.27.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
509
  "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
510
  "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
511
  "model.layers.27.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
512
  "model.layers.28.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
513
  "model.layers.28.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
514
- "model.layers.28.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
515
- "model.layers.28.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
516
- "model.layers.28.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
517
- "model.layers.28.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
518
  "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
519
  "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
520
- "model.layers.28.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
521
  "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
522
  "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
523
  "model.layers.28.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
524
- "model.layers.28.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
525
  "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
526
  "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
527
  "model.layers.28.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
528
- "model.layers.28.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
529
  "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
530
  "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
531
  "model.layers.28.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
532
- "model.layers.28.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
533
  "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
534
  "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
535
  "model.layers.28.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
536
  "model.layers.29.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
537
  "model.layers.29.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
538
- "model.layers.29.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
539
- "model.layers.29.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
540
- "model.layers.29.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
541
- "model.layers.29.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
542
  "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
543
  "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
544
- "model.layers.29.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
545
  "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
546
  "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
547
  "model.layers.29.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
548
- "model.layers.29.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
549
  "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
550
  "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
551
  "model.layers.29.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
552
- "model.layers.29.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
553
  "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
554
  "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
555
  "model.layers.29.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
556
- "model.layers.29.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
557
  "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
558
  "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
559
  "model.layers.29.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
560
  "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
561
  "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
562
- "model.layers.3.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
563
- "model.layers.3.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
564
- "model.layers.3.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
565
- "model.layers.3.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
566
  "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
567
  "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
568
- "model.layers.3.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
569
  "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
570
  "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
571
  "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
572
- "model.layers.3.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
573
  "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
574
  "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
575
  "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
576
- "model.layers.3.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
577
  "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
578
  "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
579
  "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
580
- "model.layers.3.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
581
  "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
582
  "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
583
  "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
584
  "model.layers.30.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
585
  "model.layers.30.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
586
- "model.layers.30.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
587
- "model.layers.30.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
588
- "model.layers.30.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
589
- "model.layers.30.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
590
  "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
591
  "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
592
- "model.layers.30.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
593
  "model.layers.30.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
594
  "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
595
  "model.layers.30.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
596
- "model.layers.30.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
597
  "model.layers.30.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
598
  "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
599
  "model.layers.30.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
600
- "model.layers.30.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
601
  "model.layers.30.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
602
  "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
603
  "model.layers.30.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
604
- "model.layers.30.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
605
  "model.layers.30.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
606
  "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
607
  "model.layers.30.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
608
  "model.layers.31.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
609
  "model.layers.31.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
610
- "model.layers.31.block_sparse_moe.router.layer.weight_g_idx": "model-00002-of-00002.safetensors",
611
- "model.layers.31.block_sparse_moe.router.layer.weight_packed": "model-00002-of-00002.safetensors",
612
- "model.layers.31.block_sparse_moe.router.layer.weight_scale": "model-00002-of-00002.safetensors",
613
- "model.layers.31.block_sparse_moe.router.layer.weight_shape": "model-00002-of-00002.safetensors",
614
  "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
615
  "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
616
- "model.layers.31.self_attn.k_proj.weight_g_idx": "model-00002-of-00002.safetensors",
617
  "model.layers.31.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
618
  "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
619
  "model.layers.31.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
620
- "model.layers.31.self_attn.o_proj.weight_g_idx": "model-00002-of-00002.safetensors",
621
  "model.layers.31.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
622
  "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
623
  "model.layers.31.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
624
- "model.layers.31.self_attn.q_proj.weight_g_idx": "model-00002-of-00002.safetensors",
625
  "model.layers.31.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
626
  "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
627
  "model.layers.31.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
628
- "model.layers.31.self_attn.v_proj.weight_g_idx": "model-00002-of-00002.safetensors",
629
  "model.layers.31.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
630
  "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
631
  "model.layers.31.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
632
  "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
633
  "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
634
- "model.layers.4.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
635
- "model.layers.4.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
636
- "model.layers.4.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
637
- "model.layers.4.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
638
  "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
639
  "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
640
- "model.layers.4.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
641
  "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
642
  "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
643
  "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
644
- "model.layers.4.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
645
  "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
646
  "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
647
  "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
648
- "model.layers.4.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
649
  "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
650
  "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
651
  "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
652
- "model.layers.4.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
653
  "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
654
  "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
655
  "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
656
  "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
657
  "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
658
- "model.layers.5.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
659
- "model.layers.5.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
660
- "model.layers.5.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
661
- "model.layers.5.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
662
  "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
663
  "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
664
- "model.layers.5.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
665
  "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
666
  "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
667
  "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
668
- "model.layers.5.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
669
  "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
670
  "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
671
  "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
672
- "model.layers.5.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
673
  "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
674
  "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
675
  "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
676
- "model.layers.5.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
677
  "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
678
  "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
679
  "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
680
  "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
681
  "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
682
- "model.layers.6.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
683
- "model.layers.6.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
684
- "model.layers.6.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
685
- "model.layers.6.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
686
  "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
687
  "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
688
- "model.layers.6.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
689
  "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
690
  "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
691
  "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
692
- "model.layers.6.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
693
  "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
694
  "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
695
  "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
696
- "model.layers.6.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
697
  "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
698
  "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
699
  "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
700
- "model.layers.6.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
701
  "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
702
  "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
703
  "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
704
  "model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
705
  "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
706
- "model.layers.7.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
707
- "model.layers.7.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
708
- "model.layers.7.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
709
- "model.layers.7.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
710
  "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
711
  "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
712
- "model.layers.7.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
713
  "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
714
  "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
715
  "model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
716
- "model.layers.7.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
717
  "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
718
  "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
719
  "model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
720
- "model.layers.7.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
721
  "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
722
  "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
723
  "model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
724
- "model.layers.7.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
725
  "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
726
  "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
727
  "model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
728
  "model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
729
  "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
730
- "model.layers.8.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
731
- "model.layers.8.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
732
- "model.layers.8.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
733
- "model.layers.8.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
734
  "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
735
  "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
736
- "model.layers.8.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
737
  "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
738
  "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
739
  "model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
740
- "model.layers.8.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
741
  "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
742
  "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
743
  "model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
744
- "model.layers.8.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
745
  "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
746
  "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
747
  "model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
748
- "model.layers.8.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
749
  "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
750
  "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
751
  "model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
752
  "model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
753
  "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
754
- "model.layers.9.block_sparse_moe.router.layer.weight_g_idx": "model-00001-of-00002.safetensors",
755
- "model.layers.9.block_sparse_moe.router.layer.weight_packed": "model-00001-of-00002.safetensors",
756
- "model.layers.9.block_sparse_moe.router.layer.weight_scale": "model-00001-of-00002.safetensors",
757
- "model.layers.9.block_sparse_moe.router.layer.weight_shape": "model-00001-of-00002.safetensors",
758
  "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
759
  "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
760
- "model.layers.9.self_attn.k_proj.weight_g_idx": "model-00001-of-00002.safetensors",
761
  "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
762
  "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
763
  "model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
764
- "model.layers.9.self_attn.o_proj.weight_g_idx": "model-00001-of-00002.safetensors",
765
  "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
766
  "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
767
  "model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
768
- "model.layers.9.self_attn.q_proj.weight_g_idx": "model-00001-of-00002.safetensors",
769
  "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
770
  "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
771
  "model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
772
- "model.layers.9.self_attn.v_proj.weight_g_idx": "model-00001-of-00002.safetensors",
773
  "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
774
  "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
775
  "model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 6449748992
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00002-of-00002.safetensors",
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
  "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
9
  "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
11
  "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
12
  "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
13
  "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
14
  "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
15
  "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
16
  "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
17
  "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
18
  "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
19
  "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
20
  "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
21
  "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
22
  "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
23
  "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
24
  "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
25
  "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
26
  "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
28
  "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
30
  "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
31
  "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
32
  "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
33
  "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
34
  "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
35
  "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
36
  "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
37
  "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
38
  "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
39
  "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
40
  "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
41
  "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
42
  "model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
43
  "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
45
  "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
  "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
47
  "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
48
  "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
49
  "model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
50
  "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
51
  "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
52
  "model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
53
  "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
54
  "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
55
  "model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
56
  "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
57
  "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
58
  "model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
59
  "model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
60
  "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
62
  "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
  "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
64
  "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
65
  "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
66
  "model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
67
  "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
68
  "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
69
  "model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
70
  "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
71
  "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
72
  "model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
73
  "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
74
  "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
75
  "model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
76
  "model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
77
  "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
79
  "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
  "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
81
  "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
82
  "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
83
  "model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
84
  "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
85
  "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
86
  "model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
87
  "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
88
  "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
89
  "model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
90
  "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
91
  "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
92
  "model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
93
  "model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
94
  "model.layers.13.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.13.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
96
  "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
  "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
98
  "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
99
  "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
100
  "model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
101
  "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
102
  "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
103
  "model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
104
  "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
105
  "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
106
  "model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
107
  "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
108
  "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
109
  "model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
110
  "model.layers.14.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
111
  "model.layers.14.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.14.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
113
  "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
114
  "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
115
  "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
116
  "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
117
  "model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
118
  "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
119
  "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
120
  "model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
121
  "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
122
  "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
123
  "model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
124
  "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
125
  "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
126
  "model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
127
  "model.layers.15.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
128
  "model.layers.15.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.15.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
130
  "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
131
  "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
132
  "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
133
  "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
134
  "model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
135
  "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
136
  "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
137
  "model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
138
  "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
139
  "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
140
  "model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
141
  "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
142
  "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
143
  "model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
144
  "model.layers.16.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
145
  "model.layers.16.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.16.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
147
  "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
  "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
149
  "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
150
  "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
151
  "model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
152
  "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
153
  "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
154
  "model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
155
  "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
156
  "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
157
  "model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
158
  "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
159
  "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
160
  "model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
161
  "model.layers.17.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
162
  "model.layers.17.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.17.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
164
  "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
  "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
166
  "model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
167
  "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
168
  "model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
169
  "model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
170
  "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
171
  "model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
172
  "model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
173
  "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
174
  "model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
175
  "model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
176
  "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
177
  "model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
178
  "model.layers.18.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
179
  "model.layers.18.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.18.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
181
  "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
  "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
183
  "model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
184
  "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
185
  "model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
186
  "model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
187
  "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
188
  "model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
189
  "model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
190
  "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
191
  "model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
192
  "model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
193
  "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
194
  "model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
195
  "model.layers.19.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
196
  "model.layers.19.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.19.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
198
  "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
  "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
200
  "model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
201
  "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
202
  "model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
203
  "model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
204
  "model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
205
  "model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
206
  "model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
207
  "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
208
  "model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
209
  "model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
210
  "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
211
  "model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
212
  "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
213
  "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
215
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
  "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
217
  "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
218
  "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
219
  "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
220
  "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
221
  "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
222
  "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
223
  "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
224
  "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
225
  "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
226
  "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
227
  "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
228
  "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
229
  "model.layers.20.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
230
  "model.layers.20.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.20.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
232
  "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
  "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
234
  "model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
235
  "model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
236
  "model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
237
  "model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
238
  "model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
239
  "model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
240
  "model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
241
  "model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
242
  "model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
243
  "model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
244
  "model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
245
  "model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
246
  "model.layers.21.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
247
  "model.layers.21.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.21.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
249
  "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
250
  "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
251
  "model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
252
  "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
253
  "model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
254
  "model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
255
  "model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
256
  "model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
257
  "model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
258
  "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
259
  "model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
260
  "model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
261
  "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
262
  "model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
263
  "model.layers.22.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
264
  "model.layers.22.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.22.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
266
  "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
267
  "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
268
  "model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
269
  "model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
270
  "model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
271
  "model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
272
  "model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
273
  "model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
274
  "model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
275
  "model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
276
  "model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
277
  "model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
278
  "model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
279
  "model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
280
  "model.layers.23.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
281
  "model.layers.23.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.23.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
283
  "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
  "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
285
  "model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
286
  "model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
287
  "model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
288
  "model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
289
  "model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
290
  "model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
291
  "model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
292
  "model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
293
  "model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
294
  "model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
295
  "model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
296
  "model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
297
  "model.layers.24.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
298
  "model.layers.24.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.24.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
300
  "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
301
  "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
302
  "model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
303
  "model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
304
  "model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
305
  "model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
306
  "model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
307
  "model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
308
  "model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
309
  "model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
310
  "model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
311
  "model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
312
  "model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
313
  "model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
314
  "model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
315
  "model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.25.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
317
  "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
318
  "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
319
  "model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
320
  "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
321
  "model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
322
  "model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
323
  "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
324
  "model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
325
  "model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
326
  "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
327
  "model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
328
  "model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
329
  "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
330
  "model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
331
  "model.layers.26.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
332
  "model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
334
  "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
335
  "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
336
  "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
337
  "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
338
  "model.layers.26.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
339
  "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
340
  "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
341
  "model.layers.26.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
342
  "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
343
  "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
344
  "model.layers.26.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
345
  "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
346
  "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
347
  "model.layers.26.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
348
  "model.layers.27.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
349
  "model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
351
  "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
352
  "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
353
  "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
354
  "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
355
  "model.layers.27.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
356
  "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
357
  "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
358
  "model.layers.27.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
359
  "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
360
  "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
361
  "model.layers.27.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
362
  "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
363
  "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
364
  "model.layers.27.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
365
  "model.layers.28.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
366
  "model.layers.28.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.28.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
368
  "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
369
  "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
370
  "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
371
  "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
372
  "model.layers.28.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
373
  "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
374
  "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
375
  "model.layers.28.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
376
  "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
377
  "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
378
  "model.layers.28.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
379
  "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
380
  "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
381
  "model.layers.28.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
382
  "model.layers.29.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
383
  "model.layers.29.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.29.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
385
  "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
386
  "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
387
  "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
388
  "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
389
  "model.layers.29.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
390
  "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
391
  "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
392
  "model.layers.29.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
393
  "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
394
  "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
395
  "model.layers.29.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
396
  "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
397
  "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
398
  "model.layers.29.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
399
  "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
400
  "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
402
  "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
403
  "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
404
  "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
405
  "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
406
  "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
407
  "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
408
  "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
409
  "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
410
  "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
411
  "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
412
  "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
413
  "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
414
  "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
415
  "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
416
  "model.layers.30.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
417
  "model.layers.30.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
418
+ "model.layers.30.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
419
  "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
420
  "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
421
  "model.layers.30.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
422
  "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
423
  "model.layers.30.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
424
  "model.layers.30.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
425
  "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
426
  "model.layers.30.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
427
  "model.layers.30.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
428
  "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
429
  "model.layers.30.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
430
  "model.layers.30.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
431
  "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
432
  "model.layers.30.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
433
  "model.layers.31.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
434
  "model.layers.31.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
435
+ "model.layers.31.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
 
 
 
436
  "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
437
  "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
 
438
  "model.layers.31.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
439
  "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
440
  "model.layers.31.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
 
441
  "model.layers.31.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
442
  "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
443
  "model.layers.31.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
 
444
  "model.layers.31.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
445
  "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
446
  "model.layers.31.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
 
447
  "model.layers.31.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
448
  "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
449
  "model.layers.31.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
450
  "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
451
  "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
453
  "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
454
  "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
455
  "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
456
  "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
457
  "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
458
  "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
459
  "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
460
  "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
461
  "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
462
  "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
463
  "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
464
  "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
465
  "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
466
  "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
467
  "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
468
  "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
469
+ "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
470
  "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
471
  "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
472
  "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
473
  "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
474
  "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
475
  "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
476
  "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
477
  "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
478
  "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
479
  "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
480
  "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
481
  "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
482
  "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
483
  "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
484
  "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
485
  "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
486
+ "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
487
  "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
488
  "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
489
  "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
490
  "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
491
  "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
492
  "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
493
  "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
494
  "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
495
  "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
496
  "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
497
  "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
498
  "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
499
  "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
500
  "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
501
  "model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
502
  "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
503
+ "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
504
  "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
505
  "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
506
  "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
507
  "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
508
  "model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
509
  "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
510
  "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
511
  "model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
512
  "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
513
  "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
514
  "model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
515
  "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
516
  "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
517
  "model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
518
  "model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
519
  "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
520
+ "model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
521
  "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
522
  "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
523
  "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
524
  "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
525
  "model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
526
  "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
527
  "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
528
  "model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
529
  "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
530
  "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
531
  "model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
532
  "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
533
  "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
534
  "model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
535
  "model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
536
  "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
537
+ "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
 
 
 
538
  "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
539
  "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
540
  "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
541
  "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
542
  "model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
 
543
  "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
544
  "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
545
  "model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
 
546
  "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
547
  "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
548
  "model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
 
549
  "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
550
  "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
551
  "model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
recipe.yaml CHANGED
@@ -3,9 +3,9 @@ quant_stage:
3
  GPTQModifier:
4
  sequential_update: true
5
  dampening_frac: 0.01
6
- ignore: [lm_head]
7
  config_groups:
8
  group_0:
9
  weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128,
10
- actorder: group, observer: mse}
11
  targets: [Linear]
 
3
  GPTQModifier:
4
  sequential_update: true
5
  dampening_frac: 0.01
6
+ ignore: [lm_head, 're:.*router*']
7
  config_groups:
8
  group_0:
9
  weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128,
10
+ actorder: weight, observer: mse}
11
  targets: [Linear]
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 8196,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {