freeCS-dot-org commited on
Commit
33fa719
1 Parent(s): cee429b

Upload 11 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
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": "float16",
30
+ "transformers_version": "4.37.0.dev0",
31
+ "vocab_size": 51200
32
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.0.dev0"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8099fb41851fd2428dc8d495d3b4b8f6ef4ae06cd3faf51ae6fbb30ec4792d
3
+ size 4982467864
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb39636ea36003a1be02e2dfca578d746ce8ca456bb5cb5730cf1919feb2443f
3
+ size 576934128
model.safetensors.index.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5559367680
4
+ },
5
+ "weight_map": {
6
+ "lm_head.linear.bias": "model-00002-of-00002.safetensors",
7
+ "lm_head.linear.weight": "model-00002-of-00002.safetensors",
8
+ "lm_head.ln.bias": "model-00002-of-00002.safetensors",
9
+ "lm_head.ln.weight": "model-00002-of-00002.safetensors",
10
+ "transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
20
+ "transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
+ "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
42
+ "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
44
+ "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
51
+ "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
52
+ "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
53
+ "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
54
+ "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
55
+ "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
56
+ "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
57
+ "transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
62
+ "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
64
+ "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
66
+ "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
68
+ "transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
70
+ "transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
72
+ "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
73
+ "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
74
+ "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
76
+ "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
77
+ "transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
78
+ "transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
79
+ "transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
80
+ "transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
81
+ "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
82
+ "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
83
+ "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
84
+ "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
86
+ "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
88
+ "transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
90
+ "transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
92
+ "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
94
+ "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
96
+ "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
+ "transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
+ "transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
+ "transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
102
+ "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
103
+ "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
104
+ "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
105
+ "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
106
+ "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
107
+ "transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
108
+ "transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
109
+ "transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
110
+ "transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
111
+ "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
114
+ "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
115
+ "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
116
+ "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
117
+ "transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
118
+ "transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
119
+ "transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
120
+ "transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
122
+ "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
123
+ "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
124
+ "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
125
+ "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
126
+ "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
127
+ "transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
128
+ "transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
129
+ "transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
130
+ "transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
131
+ "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
132
+ "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
133
+ "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
134
+ "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
135
+ "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
136
+ "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
137
+ "transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
138
+ "transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
139
+ "transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
140
+ "transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
142
+ "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
143
+ "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
144
+ "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
146
+ "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
148
+ "transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
150
+ "transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
151
+ "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
152
+ "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
154
+ "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
155
+ "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
156
+ "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
157
+ "transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
158
+ "transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
159
+ "transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
160
+ "transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
161
+ "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
162
+ "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
163
+ "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
166
+ "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
+ "transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
+ "transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
172
+ "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
174
+ "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
175
+ "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
176
+ "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
177
+ "transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
178
+ "transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
180
+ "transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
181
+ "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
182
+ "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
183
+ "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
184
+ "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
185
+ "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
186
+ "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
187
+ "transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
188
+ "transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
190
+ "transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
192
+ "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
194
+ "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
196
+ "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
198
+ "transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
199
+ "transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
200
+ "transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
201
+ "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
202
+ "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
203
+ "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
204
+ "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
205
+ "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
206
+ "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
207
+ "transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
208
+ "transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
209
+ "transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
210
+ "transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
211
+ "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
212
+ "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
213
+ "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
214
+ "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
215
+ "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
216
+ "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
217
+ "transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
218
+ "transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
219
+ "transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
222
+ "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
223
+ "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
224
+ "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
225
+ "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
226
+ "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
227
+ "transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
228
+ "transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
229
+ "transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
230
+ "transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
231
+ "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
232
+ "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
233
+ "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
234
+ "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
235
+ "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
236
+ "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
237
+ "transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
+ "transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
+ "transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
+ "transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
242
+ "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
243
+ "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
244
+ "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
246
+ "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
247
+ "transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
248
+ "transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
250
+ "transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
251
+ "transformer.h.30.ln.bias": "model-00001-of-00002.safetensors",
252
+ "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
254
+ "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
255
+ "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
256
+ "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
257
+ "transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
258
+ "transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
259
+ "transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
260
+ "transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
261
+ "transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
262
+ "transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
263
+ "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
264
+ "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
265
+ "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
266
+ "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
267
+ "transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
268
+ "transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
269
+ "transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
270
+ "transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
271
+ "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
272
+ "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
274
+ "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
275
+ "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
276
+ "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
277
+ "transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
278
+ "transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
279
+ "transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
280
+ "transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
281
+ "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
282
+ "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
283
+ "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
284
+ "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
285
+ "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
286
+ "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
287
+ "transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
288
+ "transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
289
+ "transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
290
+ "transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
291
+ "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
292
+ "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
294
+ "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
295
+ "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
296
+ "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
298
+ "transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
299
+ "transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
300
+ "transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
302
+ "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
303
+ "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
304
+ "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
306
+ "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
307
+ "transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
308
+ "transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
309
+ "transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
310
+ "transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
311
+ "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
312
+ "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
313
+ "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
314
+ "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
315
+ "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
316
+ "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
317
+ "transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
318
+ "transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
319
+ "transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
320
+ "transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
321
+ "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
322
+ "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
323
+ "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
324
+ "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
325
+ "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
326
+ "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
327
+ "transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
328
+ "transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
329
+ "transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
330
+ "transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors"
331
+ }
332
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "tokenizer_class": "CodeGenTokenizer",
322
+ "unk_token": "<|endoftext|>"
323
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff