wenbopan commited on
Commit
adecdb1
1 Parent(s): cb89505

Faro DPO model

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cephfs/panwenbo/work/models/Faro-9B-DPO",
3
+ "architectures": [
4
+ "LlamaModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.39.3",
27
+ "use_cache": false,
28
+ "vocab_size": 64000
29
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cbc68af8cf67097bd006077715fa48ff4070ada1bf71ff11479147ee49b3f18
3
+ size 4932710736
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc40bb49b9c21e5c54870bf3fe0be42080eebf48fdee787984e0ac8b9ca7dc2
3
+ size 4976802024
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea77673a7dcfd3a17d950622092219fecc81132fa0ad0cca400cabdcc4c1e6bb
3
+ size 4968396592
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4204f4e493961e3119c40dfb6f4f3311b62078fe82e326e26e6936e99bd788d
3
+ size 2256664904
model.safetensors.index.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17134526464
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
27
+ "layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
28
+ "layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
29
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
30
+ "layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
31
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
32
+ "layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
33
+ "layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
34
+ "layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
35
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
36
+ "layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
37
+ "layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
38
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
39
+ "layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
40
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
41
+ "layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
42
+ "layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
43
+ "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
46
+ "layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
47
+ "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
49
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
50
+ "layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
51
+ "layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
52
+ "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
71
+ "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
72
+ "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
73
+ "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
74
+ "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
81
+ "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
82
+ "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
83
+ "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
84
+ "layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
85
+ "layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
86
+ "layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
87
+ "layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
88
+ "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
90
+ "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
91
+ "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
92
+ "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
94
+ "layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
95
+ "layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
115
+ "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
125
+ "layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
126
+ "layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
127
+ "layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
128
+ "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
130
+ "layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
131
+ "layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
132
+ "layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
133
+ "layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
135
+ "layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
136
+ "layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
137
+ "layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
138
+ "layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
139
+ "layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
140
+ "layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
141
+ "layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
142
+ "layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
143
+ "layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
144
+ "layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
145
+ "layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
146
+ "layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
147
+ "layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
148
+ "layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
149
+ "layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
150
+ "layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
151
+ "layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
152
+ "layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
153
+ "layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
154
+ "layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
155
+ "layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
156
+ "layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
157
+ "layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
158
+ "layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
159
+ "layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
160
+ "layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
161
+ "layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
162
+ "layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
163
+ "layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
164
+ "layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
165
+ "layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
166
+ "layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
167
+ "layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
168
+ "layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
169
+ "layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
170
+ "layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
171
+ "layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
172
+ "layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
173
+ "layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
174
+ "layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
175
+ "layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
176
+ "layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
177
+ "layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
178
+ "layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
179
+ "layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
180
+ "layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
181
+ "layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
182
+ "layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
183
+ "layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
184
+ "layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
185
+ "layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
186
+ "layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
187
+ "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
189
+ "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
190
+ "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
191
+ "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
192
+ "layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
193
+ "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
194
+ "layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
195
+ "layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
196
+ "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
211
+ "layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
212
+ "layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
213
+ "layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
214
+ "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
224
+ "layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
225
+ "layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
226
+ "layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
227
+ "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
229
+ "layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
230
+ "layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
231
+ "layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
232
+ "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
234
+ "layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
235
+ "layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
236
+ "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
238
+ "layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
239
+ "layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
240
+ "layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
241
+ "layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
243
+ "layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
244
+ "layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
245
+ "layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
246
+ "layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
249
+ "layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
250
+ "layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
251
+ "layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
252
+ "layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
253
+ "layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
254
+ "layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
259
+ "layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
260
+ "layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
261
+ "layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
262
+ "layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
263
+ "layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
264
+ "layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
265
+ "layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
266
+ "layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
267
+ "layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
268
+ "layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
269
+ "layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
270
+ "layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
271
+ "layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
272
+ "layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
273
+ "layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
274
+ "layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
275
+ "layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
276
+ "layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
277
+ "layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
279
+ "layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
280
+ "layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
281
+ "layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
282
+ "layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
283
+ "layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
284
+ "layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
285
+ "layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
286
+ "layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
288
+ "layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
289
+ "layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
290
+ "layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
291
+ "layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
292
+ "layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
293
+ "layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
+ "layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
+ "layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
+ "layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
301
+ "layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
302
+ "layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
303
+ "layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
304
+ "layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
305
+ "layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
306
+ "layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
307
+ "layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
308
+ "layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
309
+ "layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
310
+ "layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
311
+ "layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
312
+ "layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
313
+ "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
315
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
316
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
317
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
318
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
319
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
320
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
321
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
322
+ "layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
323
+ "layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
324
+ "layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
325
+ "layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
326
+ "layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
327
+ "layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
328
+ "layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
329
+ "layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
330
+ "layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
331
+ "layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
332
+ "layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
333
+ "layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
334
+ "layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
335
+ "layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
336
+ "layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
337
+ "layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
338
+ "layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
339
+ "layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
340
+ "layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
341
+ "layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
342
+ "layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
343
+ "layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
344
+ "layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
345
+ "layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
346
+ "layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
347
+ "layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
348
+ "layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
349
+ "layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
350
+ "layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
351
+ "layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
352
+ "layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
353
+ "layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
354
+ "layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
355
+ "layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
356
+ "layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
357
+ "layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
358
+ "layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
359
+ "layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
360
+ "layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
361
+ "layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
362
+ "layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
363
+ "layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
364
+ "layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
365
+ "layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
366
+ "layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
367
+ "layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
368
+ "layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
369
+ "layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
370
+ "layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
371
+ "layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
372
+ "layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
373
+ "layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
374
+ "layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
375
+ "layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
376
+ "layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
377
+ "layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
378
+ "layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
379
+ "layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
380
+ "layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
381
+ "layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
382
+ "layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
383
+ "layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
384
+ "layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
385
+ "layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
386
+ "layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
387
+ "layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
388
+ "layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
389
+ "layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
390
+ "layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
391
+ "layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
392
+ "layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
393
+ "layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
394
+ "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
395
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
396
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
397
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
398
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
399
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
400
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
401
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
402
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
403
+ "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
404
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
405
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
406
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
407
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
408
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
409
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
410
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
411
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
412
+ "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
413
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
414
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
415
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
417
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
418
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
419
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
420
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
421
+ "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
422
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
423
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
424
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
425
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
426
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
428
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
429
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
430
+ "layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
431
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
432
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
433
+ "layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
434
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
435
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
436
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
437
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
438
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
439
+ "norm.weight": "model-00004-of-00004.safetensors"
440
+ }
441
+ }