nakulz commited on
Commit
da3a255
1 Parent(s): ec010ba

Upload PhiForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PhiForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
10
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
11
+ },
12
+ "embd_pdrop": 0.0,
13
+ "flash_attn": false,
14
+ "flash_rotary": false,
15
+ "fused_dense": false,
16
+ "img_processor": null,
17
+ "initializer_range": 0.02,
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "phi-msft",
20
+ "n_embd": 2560,
21
+ "n_head": 32,
22
+ "n_head_kv": null,
23
+ "n_inner": null,
24
+ "n_layer": 32,
25
+ "n_positions": 2048,
26
+ "resid_pdrop": 0.1,
27
+ "rotary_dim": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.2",
31
+ "vocab_size": 51200
32
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.36.2"
4
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7362926f97e3b4bcbbb71b3a31d0c0acb38c526dc2df6124d80e9e002af79d71
3
+ size 4929919720
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380208a128d58e75fd04f5a81f36afbf02184efdac350f132ad13ed13ac4437f
3
+ size 4930095280
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5bc663f9ffb95d0b1781bcc86d07b6502cd1407749f52cb0725361dd2ad5d09
3
+ size 1258754696
model.safetensors.index.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11118735360
4
+ },
5
+ "weight_map": {
6
+ "lm_head.linear.bias": "model-00003-of-00003.safetensors",
7
+ "lm_head.linear.weight": "model-00003-of-00003.safetensors",
8
+ "lm_head.ln.bias": "model-00003-of-00003.safetensors",
9
+ "lm_head.ln.weight": "model-00003-of-00003.safetensors",
10
+ "transformer.embd.wte.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.ln.bias": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.ln.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
18
+ "transformer.h.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
20
+ "transformer.h.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.ln.bias": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.ln.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
30
+ "transformer.h.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
31
+ "transformer.h.10.ln.bias": "model-00001-of-00003.safetensors",
32
+ "transformer.h.10.ln.weight": "model-00001-of-00003.safetensors",
33
+ "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
34
+ "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
36
+ "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
38
+ "transformer.h.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.h.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
40
+ "transformer.h.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
41
+ "transformer.h.11.ln.bias": "model-00001-of-00003.safetensors",
42
+ "transformer.h.11.ln.weight": "model-00001-of-00003.safetensors",
43
+ "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
44
+ "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
45
+ "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
46
+ "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
47
+ "transformer.h.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
48
+ "transformer.h.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
50
+ "transformer.h.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
51
+ "transformer.h.12.ln.bias": "model-00001-of-00003.safetensors",
52
+ "transformer.h.12.ln.weight": "model-00001-of-00003.safetensors",
53
+ "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
54
+ "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
55
+ "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
56
+ "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
57
+ "transformer.h.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
58
+ "transformer.h.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.h.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
60
+ "transformer.h.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
61
+ "transformer.h.13.ln.bias": "model-00001-of-00003.safetensors",
62
+ "transformer.h.13.ln.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
64
+ "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
65
+ "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
66
+ "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.h.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
68
+ "transformer.h.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.h.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
70
+ "transformer.h.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.h.14.ln.bias": "model-00001-of-00003.safetensors",
72
+ "transformer.h.14.ln.weight": "model-00001-of-00003.safetensors",
73
+ "transformer.h.14.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
74
+ "transformer.h.14.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
75
+ "transformer.h.14.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
76
+ "transformer.h.14.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
77
+ "transformer.h.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
78
+ "transformer.h.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
79
+ "transformer.h.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
80
+ "transformer.h.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
81
+ "transformer.h.15.ln.bias": "model-00002-of-00003.safetensors",
82
+ "transformer.h.15.ln.weight": "model-00002-of-00003.safetensors",
83
+ "transformer.h.15.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
84
+ "transformer.h.15.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
85
+ "transformer.h.15.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
86
+ "transformer.h.15.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
88
+ "transformer.h.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
89
+ "transformer.h.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
90
+ "transformer.h.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
91
+ "transformer.h.16.ln.bias": "model-00002-of-00003.safetensors",
92
+ "transformer.h.16.ln.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.16.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
94
+ "transformer.h.16.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.16.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
96
+ "transformer.h.16.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.h.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
98
+ "transformer.h.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
99
+ "transformer.h.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
100
+ "transformer.h.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.17.ln.bias": "model-00002-of-00003.safetensors",
102
+ "transformer.h.17.ln.weight": "model-00002-of-00003.safetensors",
103
+ "transformer.h.17.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
104
+ "transformer.h.17.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
105
+ "transformer.h.17.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
106
+ "transformer.h.17.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
107
+ "transformer.h.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
108
+ "transformer.h.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
109
+ "transformer.h.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
110
+ "transformer.h.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
111
+ "transformer.h.18.ln.bias": "model-00002-of-00003.safetensors",
112
+ "transformer.h.18.ln.weight": "model-00002-of-00003.safetensors",
113
+ "transformer.h.18.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
114
+ "transformer.h.18.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
115
+ "transformer.h.18.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
116
+ "transformer.h.18.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
117
+ "transformer.h.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
118
+ "transformer.h.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
119
+ "transformer.h.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
120
+ "transformer.h.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
121
+ "transformer.h.19.ln.bias": "model-00002-of-00003.safetensors",
122
+ "transformer.h.19.ln.weight": "model-00002-of-00003.safetensors",
123
+ "transformer.h.19.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
124
+ "transformer.h.19.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
125
+ "transformer.h.19.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
126
+ "transformer.h.19.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
127
+ "transformer.h.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
128
+ "transformer.h.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
129
+ "transformer.h.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
130
+ "transformer.h.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
131
+ "transformer.h.2.ln.bias": "model-00001-of-00003.safetensors",
132
+ "transformer.h.2.ln.weight": "model-00001-of-00003.safetensors",
133
+ "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
134
+ "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
135
+ "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
136
+ "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
137
+ "transformer.h.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
138
+ "transformer.h.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
139
+ "transformer.h.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
140
+ "transformer.h.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
141
+ "transformer.h.20.ln.bias": "model-00002-of-00003.safetensors",
142
+ "transformer.h.20.ln.weight": "model-00002-of-00003.safetensors",
143
+ "transformer.h.20.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
144
+ "transformer.h.20.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
145
+ "transformer.h.20.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
146
+ "transformer.h.20.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
147
+ "transformer.h.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
148
+ "transformer.h.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
149
+ "transformer.h.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
150
+ "transformer.h.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
151
+ "transformer.h.21.ln.bias": "model-00002-of-00003.safetensors",
152
+ "transformer.h.21.ln.weight": "model-00002-of-00003.safetensors",
153
+ "transformer.h.21.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
154
+ "transformer.h.21.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
155
+ "transformer.h.21.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
156
+ "transformer.h.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
157
+ "transformer.h.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
158
+ "transformer.h.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
159
+ "transformer.h.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
160
+ "transformer.h.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
161
+ "transformer.h.22.ln.bias": "model-00002-of-00003.safetensors",
162
+ "transformer.h.22.ln.weight": "model-00002-of-00003.safetensors",
163
+ "transformer.h.22.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
164
+ "transformer.h.22.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
165
+ "transformer.h.22.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
166
+ "transformer.h.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
167
+ "transformer.h.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
168
+ "transformer.h.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
169
+ "transformer.h.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
170
+ "transformer.h.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
171
+ "transformer.h.23.ln.bias": "model-00002-of-00003.safetensors",
172
+ "transformer.h.23.ln.weight": "model-00002-of-00003.safetensors",
173
+ "transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
174
+ "transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
175
+ "transformer.h.23.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
176
+ "transformer.h.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
177
+ "transformer.h.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
178
+ "transformer.h.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
179
+ "transformer.h.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
180
+ "transformer.h.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
181
+ "transformer.h.24.ln.bias": "model-00002-of-00003.safetensors",
182
+ "transformer.h.24.ln.weight": "model-00002-of-00003.safetensors",
183
+ "transformer.h.24.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
184
+ "transformer.h.24.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
185
+ "transformer.h.24.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
186
+ "transformer.h.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
187
+ "transformer.h.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
188
+ "transformer.h.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
189
+ "transformer.h.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
190
+ "transformer.h.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
191
+ "transformer.h.25.ln.bias": "model-00002-of-00003.safetensors",
192
+ "transformer.h.25.ln.weight": "model-00002-of-00003.safetensors",
193
+ "transformer.h.25.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
194
+ "transformer.h.25.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
195
+ "transformer.h.25.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
196
+ "transformer.h.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
197
+ "transformer.h.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
198
+ "transformer.h.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
199
+ "transformer.h.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
200
+ "transformer.h.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
201
+ "transformer.h.26.ln.bias": "model-00002-of-00003.safetensors",
202
+ "transformer.h.26.ln.weight": "model-00002-of-00003.safetensors",
203
+ "transformer.h.26.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
204
+ "transformer.h.26.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
205
+ "transformer.h.26.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
206
+ "transformer.h.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
207
+ "transformer.h.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
208
+ "transformer.h.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
209
+ "transformer.h.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
210
+ "transformer.h.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
211
+ "transformer.h.27.ln.bias": "model-00002-of-00003.safetensors",
212
+ "transformer.h.27.ln.weight": "model-00002-of-00003.safetensors",
213
+ "transformer.h.27.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
214
+ "transformer.h.27.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
215
+ "transformer.h.27.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
216
+ "transformer.h.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
217
+ "transformer.h.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
218
+ "transformer.h.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
219
+ "transformer.h.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
220
+ "transformer.h.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
221
+ "transformer.h.28.ln.bias": "model-00002-of-00003.safetensors",
222
+ "transformer.h.28.ln.weight": "model-00002-of-00003.safetensors",
223
+ "transformer.h.28.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
224
+ "transformer.h.28.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
225
+ "transformer.h.28.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
226
+ "transformer.h.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
227
+ "transformer.h.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
228
+ "transformer.h.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
229
+ "transformer.h.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
230
+ "transformer.h.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
231
+ "transformer.h.29.ln.bias": "model-00002-of-00003.safetensors",
232
+ "transformer.h.29.ln.weight": "model-00002-of-00003.safetensors",
233
+ "transformer.h.29.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
234
+ "transformer.h.29.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
235
+ "transformer.h.29.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
236
+ "transformer.h.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
237
+ "transformer.h.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
238
+ "transformer.h.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
239
+ "transformer.h.29.mlp.fc2.bias": "model-00003-of-00003.safetensors",
240
+ "transformer.h.29.mlp.fc2.weight": "model-00003-of-00003.safetensors",
241
+ "transformer.h.3.ln.bias": "model-00001-of-00003.safetensors",
242
+ "transformer.h.3.ln.weight": "model-00001-of-00003.safetensors",
243
+ "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
244
+ "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
245
+ "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
246
+ "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
247
+ "transformer.h.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
248
+ "transformer.h.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
249
+ "transformer.h.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
250
+ "transformer.h.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
251
+ "transformer.h.30.ln.bias": "model-00003-of-00003.safetensors",
252
+ "transformer.h.30.ln.weight": "model-00003-of-00003.safetensors",
253
+ "transformer.h.30.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
254
+ "transformer.h.30.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
255
+ "transformer.h.30.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
256
+ "transformer.h.30.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
257
+ "transformer.h.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
258
+ "transformer.h.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
259
+ "transformer.h.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
260
+ "transformer.h.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
261
+ "transformer.h.31.ln.bias": "model-00003-of-00003.safetensors",
262
+ "transformer.h.31.ln.weight": "model-00003-of-00003.safetensors",
263
+ "transformer.h.31.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
264
+ "transformer.h.31.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
265
+ "transformer.h.31.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
266
+ "transformer.h.31.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
267
+ "transformer.h.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
268
+ "transformer.h.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
269
+ "transformer.h.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
270
+ "transformer.h.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
271
+ "transformer.h.4.ln.bias": "model-00001-of-00003.safetensors",
272
+ "transformer.h.4.ln.weight": "model-00001-of-00003.safetensors",
273
+ "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
274
+ "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
275
+ "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
276
+ "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
277
+ "transformer.h.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
278
+ "transformer.h.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
279
+ "transformer.h.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
280
+ "transformer.h.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
281
+ "transformer.h.5.ln.bias": "model-00001-of-00003.safetensors",
282
+ "transformer.h.5.ln.weight": "model-00001-of-00003.safetensors",
283
+ "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
284
+ "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
285
+ "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
286
+ "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
287
+ "transformer.h.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
288
+ "transformer.h.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
289
+ "transformer.h.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
290
+ "transformer.h.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
291
+ "transformer.h.6.ln.bias": "model-00001-of-00003.safetensors",
292
+ "transformer.h.6.ln.weight": "model-00001-of-00003.safetensors",
293
+ "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
294
+ "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
295
+ "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
296
+ "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
297
+ "transformer.h.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
298
+ "transformer.h.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
299
+ "transformer.h.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
300
+ "transformer.h.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
301
+ "transformer.h.7.ln.bias": "model-00001-of-00003.safetensors",
302
+ "transformer.h.7.ln.weight": "model-00001-of-00003.safetensors",
303
+ "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
304
+ "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
305
+ "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
306
+ "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
307
+ "transformer.h.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
308
+ "transformer.h.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
309
+ "transformer.h.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
310
+ "transformer.h.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
311
+ "transformer.h.8.ln.bias": "model-00001-of-00003.safetensors",
312
+ "transformer.h.8.ln.weight": "model-00001-of-00003.safetensors",
313
+ "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
314
+ "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
315
+ "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
316
+ "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
317
+ "transformer.h.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
318
+ "transformer.h.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
319
+ "transformer.h.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
320
+ "transformer.h.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
321
+ "transformer.h.9.ln.bias": "model-00001-of-00003.safetensors",
322
+ "transformer.h.9.ln.weight": "model-00001-of-00003.safetensors",
323
+ "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
324
+ "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
325
+ "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
326
+ "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
327
+ "transformer.h.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
328
+ "transformer.h.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
329
+ "transformer.h.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
330
+ "transformer.h.9.mlp.fc2.weight": "model-00001-of-00003.safetensors"
331
+ }
332
+ }