MugoSquero commited on
Commit
d6ab7eb
1 Parent(s): 208599c

Upload of model

Browse files

Upload of the model and the script

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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Yhyu13/phi-2-sft-dpo-gpt4_en-ep1",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PhiForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "Yhyu13/phi-2-sft-dpo-gpt4_en-ep1--configuration_phi.PhiConfig",
10
+ "AutoModel": "Yhyu13/phi-2-sft-dpo-gpt4_en-ep1--modeling_phi.PhiForCausalLM",
11
+ "AutoModelForCausalLM": "Yhyu13/phi-2-sft-dpo-gpt4_en-ep1--modeling_phi.PhiForCausalLM"
12
+ },
13
+ "embd_pdrop": 0.0,
14
+ "flash_attn": false,
15
+ "flash_rotary": false,
16
+ "fused_dense": false,
17
+ "img_processor": null,
18
+ "initializer_range": 0.02,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "phi-msft",
21
+ "n_embd": 2560,
22
+ "n_head": 32,
23
+ "n_head_kv": null,
24
+ "n_inner": null,
25
+ "n_layer": 32,
26
+ "n_positions": 2048,
27
+ "resid_pdrop": 0.1,
28
+ "rotary_dim": 32,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.36.2",
32
+ "use_cache": true,
33
+ "vocab_size": 51200
34
+ }
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:be0d68094e4558dafe2240da782b8a612115c348257e95e40aa16e4f54462be7
3
+ size 4929919720
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997e1b86dc28258a15bcaff44a972d6590b7ffb956a0436b5b34e3358ac0c30a
3
+ size 4930095280
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16cafc35855185de71862a2ae85b814f59c9800fe654e0093cbd318b84fb502d
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
+ }
scripts/lmcocktail.py ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ from LM_Cocktail import mix_models_by_layers
2
+
3
+ # pip install -U LM_Cocktail && pip install sentence_transformers einops
4
+ # mix LLMs and save it to output_path: ./mixed_model_1
5
+ model = mix_models_by_layers(
6
+ model_names_or_paths=["Yhyu13/phi-2-sft-dpo-gpt4_en-ep1", "venkycs/phi-2-instruct"],
7
+ model_type='decoder',
8
+ weights=[0.5, 0.5],
9
+ output_path='./LMCocktail-phi-2-v1.1')
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 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ }
317
+ },
318
+ "bos_token": "<|endoftext|>",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "errors": "replace",
322
+ "model_max_length": 2048,
323
+ "pad_token": null,
324
+ "padding_side": "left",
325
+ "split_special_tokens": false,
326
+ "tokenizer_class": "CodeGenTokenizer",
327
+ "unk_token": "<|endoftext|>"
328
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff