TitleOS commited on
Commit
8f8e43e
1 Parent(s): 3e217d8

Initial Model Weights

Browse files
added_tokens.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|pad|>": 50296,
41
+ "<|startoftext|>": 50295
42
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_cache": false,
32
+ "vocab_size": 51200
33
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.36.2"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1160c07f43ba78e2443577aa5e147a42c903a569a7d58f3ed06eac49a30bcc05
3
+ size 4929919720
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74983c5be9ed1b80978b311adbf5f8495bc681ac2c218a327f1e4216cfe8593b
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:a3ac0dd12e5102f83ba181aff4b60345a0fbd7ab83214032e71ca614b5adb020
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7030e9bd47d5045dbb3740547f61dda05484271a978f110b392108d96fb005eb
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384e77828dfbf8c5f2b0449383f4df78ee01a422132bbd88f5c111fcf2724838
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": "<|pad|>",
11
+ "unk_token": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ }
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50295": {
317
+ "content": "<|startoftext|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50296": {
325
+ "content": "<|pad|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ }
332
+ },
333
+ "bos_token": "<|startoftext|>",
334
+ "clean_up_tokenization_spaces": true,
335
+ "eos_token": "<|endoftext|>",
336
+ "model_max_length": 2048,
337
+ "pad_token": "<|pad|>",
338
+ "tokenizer_class": "CodeGenTokenizer",
339
+ "unk_token": "<|endoftext|>"
340
+ }
trainer_state.json ADDED
@@ -0,0 +1,495 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5734456777572632,
3
+ "best_model_checkpoint": "./CodePhi2/checkpoint-750",
4
+ "epoch": 1.7492233266219035,
5
+ "eval_steps": 250,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 1.5503875968992248e-05,
14
+ "loss": 0.9039,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 3.1007751937984497e-05,
20
+ "loss": 0.59,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 4.651162790697675e-05,
26
+ "loss": 0.5942,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 6.201550387596899e-05,
32
+ "loss": 0.5905,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.12,
37
+ "learning_rate": 7.751937984496124e-05,
38
+ "loss": 0.6012,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 9.30232558139535e-05,
44
+ "loss": 0.5978,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 0.00010852713178294573,
50
+ "loss": 0.5982,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.19,
55
+ "learning_rate": 0.00012403100775193799,
56
+ "loss": 0.6037,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.21,
61
+ "learning_rate": 0.00013953488372093025,
62
+ "loss": 0.6101,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 0.0001550387596899225,
68
+ "loss": 0.6177,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.26,
73
+ "learning_rate": 0.00017054263565891473,
74
+ "loss": 0.62,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.28,
79
+ "learning_rate": 0.000186046511627907,
80
+ "loss": 0.6398,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.3,
85
+ "learning_rate": 0.00019982683982683983,
86
+ "loss": 0.6363,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.33,
91
+ "learning_rate": 0.0001980952380952381,
92
+ "loss": 0.6317,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.35,
97
+ "learning_rate": 0.00019636363636363636,
98
+ "loss": 0.6322,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.37,
103
+ "learning_rate": 0.00019463203463203463,
104
+ "loss": 0.6435,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.4,
109
+ "learning_rate": 0.00019290043290043292,
110
+ "loss": 0.6384,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.42,
115
+ "learning_rate": 0.00019116883116883119,
116
+ "loss": 0.6342,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.44,
121
+ "learning_rate": 0.00018943722943722942,
122
+ "loss": 0.626,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.47,
127
+ "learning_rate": 0.00018770562770562772,
128
+ "loss": 0.6225,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.49,
133
+ "learning_rate": 0.00018597402597402598,
134
+ "loss": 0.6195,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.51,
139
+ "learning_rate": 0.00018424242424242427,
140
+ "loss": 0.6244,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.54,
145
+ "learning_rate": 0.0001825108225108225,
146
+ "loss": 0.6292,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.56,
151
+ "learning_rate": 0.00018077922077922078,
152
+ "loss": 0.6289,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.58,
157
+ "learning_rate": 0.00017904761904761907,
158
+ "loss": 0.6331,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.58,
163
+ "eval_loss": 0.6136361360549927,
164
+ "eval_runtime": 316.7992,
165
+ "eval_samples_per_second": 38.498,
166
+ "eval_steps_per_second": 4.814,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 0.61,
171
+ "learning_rate": 0.00017731601731601733,
172
+ "loss": 0.6191,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 0.63,
177
+ "learning_rate": 0.00017558441558441557,
178
+ "loss": 0.6127,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 0.65,
183
+ "learning_rate": 0.00017385281385281386,
184
+ "loss": 0.6198,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 0.68,
189
+ "learning_rate": 0.00017212121212121213,
190
+ "loss": 0.6103,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 0.7,
195
+ "learning_rate": 0.0001703896103896104,
196
+ "loss": 0.6123,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 0.72,
201
+ "learning_rate": 0.00016865800865800866,
202
+ "loss": 0.6115,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 0.75,
207
+ "learning_rate": 0.00016692640692640693,
208
+ "loss": 0.6118,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 0.77,
213
+ "learning_rate": 0.00016519480519480522,
214
+ "loss": 0.6127,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 0.79,
219
+ "learning_rate": 0.00016346320346320348,
220
+ "loss": 0.6027,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 0.82,
225
+ "learning_rate": 0.00016173160173160172,
226
+ "loss": 0.6041,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 0.84,
231
+ "learning_rate": 0.00016,
232
+ "loss": 0.6118,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 0.86,
237
+ "learning_rate": 0.00015826839826839828,
238
+ "loss": 0.6052,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 0.89,
243
+ "learning_rate": 0.00015653679653679654,
244
+ "loss": 0.6124,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 0.91,
249
+ "learning_rate": 0.0001548051948051948,
250
+ "loss": 0.6029,
251
+ "step": 390
252
+ },
253
+ {
254
+ "epoch": 0.93,
255
+ "learning_rate": 0.00015307359307359307,
256
+ "loss": 0.6013,
257
+ "step": 400
258
+ },
259
+ {
260
+ "epoch": 0.96,
261
+ "learning_rate": 0.00015134199134199134,
262
+ "loss": 0.6006,
263
+ "step": 410
264
+ },
265
+ {
266
+ "epoch": 0.98,
267
+ "learning_rate": 0.00014961038961038963,
268
+ "loss": 0.6055,
269
+ "step": 420
270
+ },
271
+ {
272
+ "epoch": 1.0,
273
+ "learning_rate": 0.0001478787878787879,
274
+ "loss": 0.5916,
275
+ "step": 430
276
+ },
277
+ {
278
+ "epoch": 1.03,
279
+ "learning_rate": 0.00014614718614718613,
280
+ "loss": 0.4963,
281
+ "step": 440
282
+ },
283
+ {
284
+ "epoch": 1.05,
285
+ "learning_rate": 0.00014441558441558443,
286
+ "loss": 0.5066,
287
+ "step": 450
288
+ },
289
+ {
290
+ "epoch": 1.07,
291
+ "learning_rate": 0.0001426839826839827,
292
+ "loss": 0.4997,
293
+ "step": 460
294
+ },
295
+ {
296
+ "epoch": 1.1,
297
+ "learning_rate": 0.00014095238095238096,
298
+ "loss": 0.494,
299
+ "step": 470
300
+ },
301
+ {
302
+ "epoch": 1.12,
303
+ "learning_rate": 0.00013922077922077922,
304
+ "loss": 0.4925,
305
+ "step": 480
306
+ },
307
+ {
308
+ "epoch": 1.14,
309
+ "learning_rate": 0.0001374891774891775,
310
+ "loss": 0.4944,
311
+ "step": 490
312
+ },
313
+ {
314
+ "epoch": 1.17,
315
+ "learning_rate": 0.00013575757575757578,
316
+ "loss": 0.5007,
317
+ "step": 500
318
+ },
319
+ {
320
+ "epoch": 1.17,
321
+ "eval_loss": 0.5911308526992798,
322
+ "eval_runtime": 316.8116,
323
+ "eval_samples_per_second": 38.496,
324
+ "eval_steps_per_second": 4.814,
325
+ "step": 500
326
+ },
327
+ {
328
+ "epoch": 1.19,
329
+ "learning_rate": 0.00013402597402597404,
330
+ "loss": 0.5004,
331
+ "step": 510
332
+ },
333
+ {
334
+ "epoch": 1.21,
335
+ "learning_rate": 0.00013229437229437228,
336
+ "loss": 0.4985,
337
+ "step": 520
338
+ },
339
+ {
340
+ "epoch": 1.24,
341
+ "learning_rate": 0.00013056277056277057,
342
+ "loss": 0.4983,
343
+ "step": 530
344
+ },
345
+ {
346
+ "epoch": 1.26,
347
+ "learning_rate": 0.00012883116883116884,
348
+ "loss": 0.4974,
349
+ "step": 540
350
+ },
351
+ {
352
+ "epoch": 1.28,
353
+ "learning_rate": 0.0001270995670995671,
354
+ "loss": 0.4988,
355
+ "step": 550
356
+ },
357
+ {
358
+ "epoch": 1.31,
359
+ "learning_rate": 0.00012536796536796537,
360
+ "loss": 0.5051,
361
+ "step": 560
362
+ },
363
+ {
364
+ "epoch": 1.33,
365
+ "learning_rate": 0.00012363636363636364,
366
+ "loss": 0.499,
367
+ "step": 570
368
+ },
369
+ {
370
+ "epoch": 1.35,
371
+ "learning_rate": 0.00012190476190476193,
372
+ "loss": 0.5018,
373
+ "step": 580
374
+ },
375
+ {
376
+ "epoch": 1.38,
377
+ "learning_rate": 0.00012017316017316018,
378
+ "loss": 0.5027,
379
+ "step": 590
380
+ },
381
+ {
382
+ "epoch": 1.4,
383
+ "learning_rate": 0.00011844155844155844,
384
+ "loss": 0.502,
385
+ "step": 600
386
+ },
387
+ {
388
+ "epoch": 1.42,
389
+ "learning_rate": 0.00011670995670995672,
390
+ "loss": 0.4987,
391
+ "step": 610
392
+ },
393
+ {
394
+ "epoch": 1.45,
395
+ "learning_rate": 0.00011497835497835499,
396
+ "loss": 0.5002,
397
+ "step": 620
398
+ },
399
+ {
400
+ "epoch": 1.47,
401
+ "learning_rate": 0.00011324675324675324,
402
+ "loss": 0.4934,
403
+ "step": 630
404
+ },
405
+ {
406
+ "epoch": 1.49,
407
+ "learning_rate": 0.00011151515151515153,
408
+ "loss": 0.4978,
409
+ "step": 640
410
+ },
411
+ {
412
+ "epoch": 1.52,
413
+ "learning_rate": 0.00010978354978354978,
414
+ "loss": 0.4957,
415
+ "step": 650
416
+ },
417
+ {
418
+ "epoch": 1.54,
419
+ "learning_rate": 0.00010805194805194805,
420
+ "loss": 0.4958,
421
+ "step": 660
422
+ },
423
+ {
424
+ "epoch": 1.56,
425
+ "learning_rate": 0.00010632034632034633,
426
+ "loss": 0.4968,
427
+ "step": 670
428
+ },
429
+ {
430
+ "epoch": 1.59,
431
+ "learning_rate": 0.00010458874458874459,
432
+ "loss": 0.4957,
433
+ "step": 680
434
+ },
435
+ {
436
+ "epoch": 1.61,
437
+ "learning_rate": 0.00010285714285714286,
438
+ "loss": 0.4982,
439
+ "step": 690
440
+ },
441
+ {
442
+ "epoch": 1.63,
443
+ "learning_rate": 0.00010112554112554114,
444
+ "loss": 0.4968,
445
+ "step": 700
446
+ },
447
+ {
448
+ "epoch": 1.66,
449
+ "learning_rate": 9.939393939393939e-05,
450
+ "loss": 0.4951,
451
+ "step": 710
452
+ },
453
+ {
454
+ "epoch": 1.68,
455
+ "learning_rate": 9.766233766233767e-05,
456
+ "loss": 0.4952,
457
+ "step": 720
458
+ },
459
+ {
460
+ "epoch": 1.7,
461
+ "learning_rate": 9.593073593073593e-05,
462
+ "loss": 0.5001,
463
+ "step": 730
464
+ },
465
+ {
466
+ "epoch": 1.73,
467
+ "learning_rate": 9.419913419913421e-05,
468
+ "loss": 0.4982,
469
+ "step": 740
470
+ },
471
+ {
472
+ "epoch": 1.75,
473
+ "learning_rate": 9.246753246753248e-05,
474
+ "loss": 0.4945,
475
+ "step": 750
476
+ },
477
+ {
478
+ "epoch": 1.75,
479
+ "eval_loss": 0.5734456777572632,
480
+ "eval_runtime": 316.4801,
481
+ "eval_samples_per_second": 38.536,
482
+ "eval_steps_per_second": 4.819,
483
+ "step": 750
484
+ }
485
+ ],
486
+ "logging_steps": 10,
487
+ "max_steps": 1284,
488
+ "num_input_tokens_seen": 0,
489
+ "num_train_epochs": 3,
490
+ "save_steps": 250,
491
+ "total_flos": 5.360478675518669e+17,
492
+ "train_batch_size": 1,
493
+ "trial_name": null,
494
+ "trial_params": null
495
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9282ea20cbd551f42ac360b16339b1aaeb9cd1c871d210e9547d8423bfb7b9
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff