Hugging Face's logo

apple
/
DCLM-7B

Transformers
Safetensors
openlm
Inference Endpoints
Model card Files Community
11
vaishaal commited on
Commit
8afc994
•
1 Parent(s): 8d7be52

updating model files

Browse files
Files changed (8) hide show
  1. config.json +36 -0
  2. model-00001-of-00006.safetensors +3 -0
  3. model-00002-of-00006.safetensors +3 -0
  4. model-00003-of-00006.safetensors +3 -0
  5. model-00004-of-00006.safetensors +3 -0
  6. model-00005-of-00006.safetensors +3 -0
  7. model-00006-of-00006.safetensors +3 -0
  8. model.safetensors.index.json +298 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OpenLMModel"
4
+ ],
5
+ "model_type": "openlm",
6
+ "params": null,
7
+ "params_args_dict": {
8
+ "apply_qk_norm": true,
9
+ "attn_activation": null,
10
+ "attn_name": "torch_attn",
11
+ "attn_seq_scalar": null,
12
+ "attn_seq_scalar_alpha": null,
13
+ "dim": 4096,
14
+ "ffn_type": "swiglu",
15
+ "model": "open_lm_7b",
16
+ "model_norm": "gain_only_lp_layer_norm",
17
+ "moe_capacity_factor": 1.25,
18
+ "moe_expert_model_parallelism": false,
19
+ "moe_freq": 0,
20
+ "moe_loss_weight": 0.1,
21
+ "moe_num_experts": null,
22
+ "moe_top_k": 2,
23
+ "moe_weight_parallelism": false,
24
+ "n_heads": 32,
25
+ "n_layers": 32,
26
+ "norm_eps": 1e-05,
27
+ "positional_embedding_type": "rotary",
28
+ "post_embed_norm": false,
29
+ "qk_norm": true,
30
+ "seq_len": 2048,
31
+ "vocab_size": 50432,
32
+ "weight_tying": false
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.38.2"
36
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1564b98730dd7e1faeae8fe5f54b90c41a44d50c6d69ef39c208a7ff58a924a
3
+ size 4874115416
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5a67ab79c51a3b84a8c09b221de7c55a2dc0e215873f046f2ebdf78cafd7ae
3
+ size 4857404912
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c8f3c77aeac409d53cf1b08d379b0b759557c5783f1b0042bd6084e125ec0a
3
+ size 4857404960
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6045ababd025243d93b489d254ceab12bb11abd86234b9799ef5114e0b05f689
3
+ size 4857404960
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf8a14e6cd35bd6f2eac1f52809983e11d001467733344d327b239cbee6eb51
3
+ size 4857404960
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23fec6b61c7085eb44e6c7f9ebc58a19aa2feeb5ff7d906d977aa288544cf8ac
3
+ size 3254996944
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27558699008
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.in_proj.weight": "model-00001-of-00006.safetensors",
7
+ "model.layers.0.attention.k_norm.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.attention.out_proj.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.attention.pos_embed.inv_freq": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.attention.q_norm.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.attention_norm.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.feed_forward.w12.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.1.attention.in_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.1.attention.k_norm.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.attention.out_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.attention.pos_embed.inv_freq": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.attention.q_norm.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.attention_norm.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.feed_forward.w12.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.feed_forward.w3.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.10.attention.in_proj.weight": "model-00002-of-00006.safetensors",
25
+ "model.layers.10.attention.k_norm.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.10.attention.out_proj.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.attention.q_norm.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.attention_norm.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.ffn_norm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.11.attention.in_proj.weight": "model-00003-of-00006.safetensors",
34
+ "model.layers.11.attention.k_norm.weight": "model-00003-of-00006.safetensors",
35
+ "model.layers.11.attention.out_proj.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.attention.q_norm.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.attention_norm.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.ffn_norm.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.12.attention.in_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.12.attention.k_norm.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.attention.out_proj.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.attention.q_norm.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.attention_norm.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.ffn_norm.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.13.attention.in_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.13.attention.k_norm.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.attention.out_proj.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.attention.q_norm.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.attention_norm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.ffn_norm.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.14.attention.in_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.14.attention.k_norm.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.attention.out_proj.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.attention.q_norm.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.attention_norm.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.14.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.14.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.ffn_norm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.15.attention.in_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.15.attention.k_norm.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.attention.out_proj.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.attention.q_norm.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.attention_norm.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.15.ffn_norm.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.16.attention.in_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.16.attention.k_norm.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.attention.out_proj.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.16.attention.pos_embed.inv_freq": "model-00003-of-00006.safetensors",
82
+ "model.layers.16.attention.q_norm.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.attention_norm.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.16.feed_forward.w12.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.16.feed_forward.w3.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.ffn_norm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.17.attention.in_proj.weight": "model-00004-of-00006.safetensors",
88
+ "model.layers.17.attention.k_norm.weight": "model-00004-of-00006.safetensors",
89
+ "model.layers.17.attention.out_proj.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.attention.q_norm.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.attention_norm.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.ffn_norm.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.18.attention.in_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.18.attention.k_norm.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.18.attention.out_proj.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.attention.q_norm.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.attention_norm.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.ffn_norm.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.19.attention.in_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.19.attention.k_norm.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.attention.out_proj.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.attention.q_norm.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.attention_norm.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.ffn_norm.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.2.attention.in_proj.weight": "model-00001-of-00006.safetensors",
115
+ "model.layers.2.attention.k_norm.weight": "model-00001-of-00006.safetensors",
116
+ "model.layers.2.attention.out_proj.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.attention.pos_embed.inv_freq": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.attention.q_norm.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.attention_norm.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.feed_forward.w12.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.feed_forward.w3.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.20.attention.in_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.20.attention.k_norm.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.20.attention.out_proj.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.20.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
127
+ "model.layers.20.attention.q_norm.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.20.attention_norm.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.20.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.20.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.ffn_norm.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.21.attention.in_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.21.attention.k_norm.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.attention.out_proj.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.21.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
136
+ "model.layers.21.attention.q_norm.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.21.attention_norm.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.21.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.21.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.21.ffn_norm.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.22.attention.in_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.22.attention.k_norm.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.22.attention.out_proj.weight": "model-00004-of-00006.safetensors",
144
+ "model.layers.22.attention.pos_embed.inv_freq": "model-00004-of-00006.safetensors",
145
+ "model.layers.22.attention.q_norm.weight": "model-00004-of-00006.safetensors",
146
+ "model.layers.22.attention_norm.weight": "model-00004-of-00006.safetensors",
147
+ "model.layers.22.feed_forward.w12.weight": "model-00004-of-00006.safetensors",
148
+ "model.layers.22.feed_forward.w3.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.22.ffn_norm.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.23.attention.in_proj.weight": "model-00005-of-00006.safetensors",
151
+ "model.layers.23.attention.k_norm.weight": "model-00005-of-00006.safetensors",
152
+ "model.layers.23.attention.out_proj.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.attention.q_norm.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.attention_norm.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.23.ffn_norm.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.24.attention.in_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.24.attention.k_norm.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.24.attention.out_proj.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.attention.q_norm.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.attention_norm.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.ffn_norm.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.25.attention.in_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.25.attention.k_norm.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.25.attention.out_proj.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.25.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
172
+ "model.layers.25.attention.q_norm.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.25.attention_norm.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.25.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.25.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.25.ffn_norm.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.26.attention.in_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.26.attention.k_norm.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.26.attention.out_proj.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.26.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
181
+ "model.layers.26.attention.q_norm.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.26.attention_norm.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.26.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.26.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.26.ffn_norm.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.27.attention.in_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.27.attention.k_norm.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.attention.out_proj.weight": "model-00005-of-00006.safetensors",
189
+ "model.layers.27.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
190
+ "model.layers.27.attention.q_norm.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.27.attention_norm.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
193
+ "model.layers.27.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.27.ffn_norm.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.28.attention.in_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.28.attention.k_norm.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.28.attention.out_proj.weight": "model-00005-of-00006.safetensors",
198
+ "model.layers.28.attention.pos_embed.inv_freq": "model-00005-of-00006.safetensors",
199
+ "model.layers.28.attention.q_norm.weight": "model-00005-of-00006.safetensors",
200
+ "model.layers.28.attention_norm.weight": "model-00005-of-00006.safetensors",
201
+ "model.layers.28.feed_forward.w12.weight": "model-00005-of-00006.safetensors",
202
+ "model.layers.28.feed_forward.w3.weight": "model-00005-of-00006.safetensors",
203
+ "model.layers.28.ffn_norm.weight": "model-00005-of-00006.safetensors",
204
+ "model.layers.29.attention.in_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.29.attention.k_norm.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.29.attention.out_proj.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.29.attention.pos_embed.inv_freq": "model-00006-of-00006.safetensors",
208
+ "model.layers.29.attention.q_norm.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.29.attention_norm.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.29.feed_forward.w12.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.29.feed_forward.w3.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.29.ffn_norm.weight": "model-00006-of-00006.safetensors",
213
+ "model.layers.3.attention.in_proj.weight": "model-00001-of-00006.safetensors",
214
+ "model.layers.3.attention.k_norm.weight": "model-00001-of-00006.safetensors",
215
+ "model.layers.3.attention.out_proj.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.attention.pos_embed.inv_freq": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.attention.q_norm.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.attention_norm.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.feed_forward.w12.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.feed_forward.w3.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.ffn_norm.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.30.attention.in_proj.weight": "model-00006-of-00006.safetensors",
223
+ "model.layers.30.attention.k_norm.weight": "model-00006-of-00006.safetensors",
224
+ "model.layers.30.attention.out_proj.weight": "model-00006-of-00006.safetensors",
225
+ "model.layers.30.attention.pos_embed.inv_freq": "model-00006-of-00006.safetensors",
226
+ "model.layers.30.attention.q_norm.weight": "model-00006-of-00006.safetensors",
227
+ "model.layers.30.attention_norm.weight": "model-00006-of-00006.safetensors",
228
+ "model.layers.30.feed_forward.w12.weight": "model-00006-of-00006.safetensors",
229
+ "model.layers.30.feed_forward.w3.weight": "model-00006-of-00006.safetensors",
230
+ "model.layers.30.ffn_norm.weight": "model-00006-of-00006.safetensors",
231
+ "model.layers.31.attention.in_proj.weight": "model-00006-of-00006.safetensors",
232
+ "model.layers.31.attention.k_norm.weight": "model-00006-of-00006.safetensors",
233
+ "model.layers.31.attention.out_proj.weight": "model-00006-of-00006.safetensors",
234
+ "model.layers.31.attention.pos_embed.inv_freq": "model-00006-of-00006.safetensors",
235
+ "model.layers.31.attention.q_norm.weight": "model-00006-of-00006.safetensors",
236
+ "model.layers.31.attention_norm.weight": "model-00006-of-00006.safetensors",
237
+ "model.layers.31.feed_forward.w12.weight": "model-00006-of-00006.safetensors",
238
+ "model.layers.31.feed_forward.w3.weight": "model-00006-of-00006.safetensors",
239
+ "model.layers.31.ffn_norm.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.4.attention.in_proj.weight": "model-00001-of-00006.safetensors",
241
+ "model.layers.4.attention.k_norm.weight": "model-00001-of-00006.safetensors",
242
+ "model.layers.4.attention.out_proj.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.4.attention.pos_embed.inv_freq": "model-00001-of-00006.safetensors",
244
+ "model.layers.4.attention.q_norm.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.4.attention_norm.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.4.feed_forward.w12.weight": "model-00001-of-00006.safetensors",
247
+ "model.layers.4.feed_forward.w3.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.4.ffn_norm.weight": "model-00001-of-00006.safetensors",
249
+ "model.layers.5.attention.in_proj.weight": "model-00002-of-00006.safetensors",
250
+ "model.layers.5.attention.k_norm.weight": "model-00002-of-00006.safetensors",
251
+ "model.layers.5.attention.out_proj.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.5.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.attention.q_norm.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.attention_norm.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.5.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.5.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
257
+ "model.layers.5.ffn_norm.weight": "model-00002-of-00006.safetensors",
258
+ "model.layers.6.attention.in_proj.weight": "model-00002-of-00006.safetensors",
259
+ "model.layers.6.attention.k_norm.weight": "model-00002-of-00006.safetensors",
260
+ "model.layers.6.attention.out_proj.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.6.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
262
+ "model.layers.6.attention.q_norm.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.6.attention_norm.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.6.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
265
+ "model.layers.6.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
266
+ "model.layers.6.ffn_norm.weight": "model-00002-of-00006.safetensors",
267
+ "model.layers.7.attention.in_proj.weight": "model-00002-of-00006.safetensors",
268
+ "model.layers.7.attention.k_norm.weight": "model-00002-of-00006.safetensors",
269
+ "model.layers.7.attention.out_proj.weight": "model-00002-of-00006.safetensors",
270
+ "model.layers.7.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
271
+ "model.layers.7.attention.q_norm.weight": "model-00002-of-00006.safetensors",
272
+ "model.layers.7.attention_norm.weight": "model-00002-of-00006.safetensors",
273
+ "model.layers.7.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
274
+ "model.layers.7.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
275
+ "model.layers.7.ffn_norm.weight": "model-00002-of-00006.safetensors",
276
+ "model.layers.8.attention.in_proj.weight": "model-00002-of-00006.safetensors",
277
+ "model.layers.8.attention.k_norm.weight": "model-00002-of-00006.safetensors",
278
+ "model.layers.8.attention.out_proj.weight": "model-00002-of-00006.safetensors",
279
+ "model.layers.8.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
280
+ "model.layers.8.attention.q_norm.weight": "model-00002-of-00006.safetensors",
281
+ "model.layers.8.attention_norm.weight": "model-00002-of-00006.safetensors",
282
+ "model.layers.8.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
283
+ "model.layers.8.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
284
+ "model.layers.8.ffn_norm.weight": "model-00002-of-00006.safetensors",
285
+ "model.layers.9.attention.in_proj.weight": "model-00002-of-00006.safetensors",
286
+ "model.layers.9.attention.k_norm.weight": "model-00002-of-00006.safetensors",
287
+ "model.layers.9.attention.out_proj.weight": "model-00002-of-00006.safetensors",
288
+ "model.layers.9.attention.pos_embed.inv_freq": "model-00002-of-00006.safetensors",
289
+ "model.layers.9.attention.q_norm.weight": "model-00002-of-00006.safetensors",
290
+ "model.layers.9.attention_norm.weight": "model-00002-of-00006.safetensors",
291
+ "model.layers.9.feed_forward.w12.weight": "model-00002-of-00006.safetensors",
292
+ "model.layers.9.feed_forward.w3.weight": "model-00002-of-00006.safetensors",
293
+ "model.layers.9.ffn_norm.weight": "model-00002-of-00006.safetensors",
294
+ "model.norm.weight": "model-00006-of-00006.safetensors",
295
+ "model.output.weight": "model-00006-of-00006.safetensors",
296
+ "model.tok_embeddings.weight": "model-00001-of-00006.safetensors"
297
+ }
298
+ }