Brendan commited on
Commit
2b8d874
1 Parent(s): 13416f4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/starcoderbase-3b",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2816,
20
+ "n_head": 22,
21
+ "n_inner": 11264,
22
+ "n_layer": 36,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.39.1",
36
+ "use_cache": true,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.39.1"
6
+ }
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 sha256:2f7a5d141bb0089ad330824310fe9fa86f7e523d1b7228a2cbaf2a74ec87d3af
3
+ size 4874967008
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c640fed7d32450750ad2b97575df5c04748fa341e4a886128424f78fda8a9939
3
+ size 4929983264
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca52a1f308229b40a18fbf3a8c25c61c07e2e9d3ed4a9f28c127d9fdfd8cbf7
3
+ size 2368340008
model.safetensors.index.json ADDED
@@ -0,0 +1,443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12173244416
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors",
19
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00003.safetensors",
31
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
32
+ "transformer.h.10.attn.c_proj.bias": "model-00001-of-00003.safetensors",
33
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
34
+ "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
35
+ "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
37
+ "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
38
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
39
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
40
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
41
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
42
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00003.safetensors",
43
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
44
+ "transformer.h.11.attn.c_proj.bias": "model-00001-of-00003.safetensors",
45
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
47
+ "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors",
49
+ "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
51
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
53
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00003.safetensors",
55
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00003.safetensors",
56
+ "transformer.h.12.attn.c_proj.bias": "model-00001-of-00003.safetensors",
57
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors",
58
+ "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
59
+ "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
60
+ "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors",
61
+ "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
62
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
63
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
64
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
65
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
66
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00003.safetensors",
67
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00003.safetensors",
68
+ "transformer.h.13.attn.c_proj.bias": "model-00001-of-00003.safetensors",
69
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00003.safetensors",
70
+ "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
71
+ "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
72
+ "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors",
73
+ "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
75
+ "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
77
+ "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.h.14.attn.c_attn.bias": "model-00002-of-00003.safetensors",
79
+ "transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
80
+ "transformer.h.14.attn.c_proj.bias": "model-00002-of-00003.safetensors",
81
+ "transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
82
+ "transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
83
+ "transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
84
+ "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
85
+ "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
87
+ "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
89
+ "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.h.15.attn.c_attn.bias": "model-00002-of-00003.safetensors",
91
+ "transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.15.attn.c_proj.bias": "model-00002-of-00003.safetensors",
93
+ "transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
95
+ "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
97
+ "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
99
+ "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
101
+ "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.16.attn.c_attn.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.16.attn.c_proj.bias": "model-00002-of-00003.safetensors",
105
+ "transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
107
+ "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
109
+ "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
111
+ "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
112
+ "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
113
+ "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.17.attn.c_attn.bias": "model-00002-of-00003.safetensors",
115
+ "transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
116
+ "transformer.h.17.attn.c_proj.bias": "model-00002-of-00003.safetensors",
117
+ "transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
118
+ "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
119
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
120
+ "transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
121
+ "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
122
+ "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
123
+ "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
125
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.18.attn.c_attn.bias": "model-00002-of-00003.safetensors",
127
+ "transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.18.attn.c_proj.bias": "model-00002-of-00003.safetensors",
129
+ "transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
131
+ "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
133
+ "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
135
+ "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
137
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
138
+ "transformer.h.19.attn.c_attn.bias": "model-00002-of-00003.safetensors",
139
+ "transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.19.attn.c_proj.bias": "model-00002-of-00003.safetensors",
141
+ "transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
142
+ "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
143
+ "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
144
+ "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
145
+ "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
146
+ "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
147
+ "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
148
+ "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
149
+ "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00003.safetensors",
151
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
152
+ "transformer.h.2.attn.c_proj.bias": "model-00001-of-00003.safetensors",
153
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
154
+ "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
155
+ "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
156
+ "transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
157
+ "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
158
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
159
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
160
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
161
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
162
+ "transformer.h.20.attn.c_attn.bias": "model-00002-of-00003.safetensors",
163
+ "transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
164
+ "transformer.h.20.attn.c_proj.bias": "model-00002-of-00003.safetensors",
165
+ "transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
166
+ "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
167
+ "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
168
+ "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
169
+ "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
170
+ "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
171
+ "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
172
+ "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
173
+ "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
174
+ "transformer.h.21.attn.c_attn.bias": "model-00002-of-00003.safetensors",
175
+ "transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
176
+ "transformer.h.21.attn.c_proj.bias": "model-00002-of-00003.safetensors",
177
+ "transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
178
+ "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
179
+ "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
180
+ "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
181
+ "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
182
+ "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
183
+ "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
184
+ "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
185
+ "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
186
+ "transformer.h.22.attn.c_attn.bias": "model-00002-of-00003.safetensors",
187
+ "transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
188
+ "transformer.h.22.attn.c_proj.bias": "model-00002-of-00003.safetensors",
189
+ "transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
190
+ "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
191
+ "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
192
+ "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
193
+ "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
194
+ "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
195
+ "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
196
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
197
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
198
+ "transformer.h.23.attn.c_attn.bias": "model-00002-of-00003.safetensors",
199
+ "transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
200
+ "transformer.h.23.attn.c_proj.bias": "model-00002-of-00003.safetensors",
201
+ "transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
202
+ "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
203
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
204
+ "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
205
+ "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
206
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
207
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
208
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
209
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
210
+ "transformer.h.24.attn.c_attn.bias": "model-00002-of-00003.safetensors",
211
+ "transformer.h.24.attn.c_attn.weight": "model-00002-of-00003.safetensors",
212
+ "transformer.h.24.attn.c_proj.bias": "model-00002-of-00003.safetensors",
213
+ "transformer.h.24.attn.c_proj.weight": "model-00002-of-00003.safetensors",
214
+ "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
215
+ "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
216
+ "transformer.h.24.ln_2.bias": "model-00002-of-00003.safetensors",
217
+ "transformer.h.24.ln_2.weight": "model-00002-of-00003.safetensors",
218
+ "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
219
+ "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
220
+ "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
221
+ "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
222
+ "transformer.h.25.attn.c_attn.bias": "model-00002-of-00003.safetensors",
223
+ "transformer.h.25.attn.c_attn.weight": "model-00002-of-00003.safetensors",
224
+ "transformer.h.25.attn.c_proj.bias": "model-00002-of-00003.safetensors",
225
+ "transformer.h.25.attn.c_proj.weight": "model-00002-of-00003.safetensors",
226
+ "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
227
+ "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
228
+ "transformer.h.25.ln_2.bias": "model-00002-of-00003.safetensors",
229
+ "transformer.h.25.ln_2.weight": "model-00002-of-00003.safetensors",
230
+ "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
231
+ "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
232
+ "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
233
+ "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
234
+ "transformer.h.26.attn.c_attn.bias": "model-00002-of-00003.safetensors",
235
+ "transformer.h.26.attn.c_attn.weight": "model-00002-of-00003.safetensors",
236
+ "transformer.h.26.attn.c_proj.bias": "model-00002-of-00003.safetensors",
237
+ "transformer.h.26.attn.c_proj.weight": "model-00002-of-00003.safetensors",
238
+ "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
239
+ "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
240
+ "transformer.h.26.ln_2.bias": "model-00002-of-00003.safetensors",
241
+ "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
242
+ "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
243
+ "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
244
+ "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
245
+ "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
246
+ "transformer.h.27.attn.c_attn.bias": "model-00002-of-00003.safetensors",
247
+ "transformer.h.27.attn.c_attn.weight": "model-00002-of-00003.safetensors",
248
+ "transformer.h.27.attn.c_proj.bias": "model-00002-of-00003.safetensors",
249
+ "transformer.h.27.attn.c_proj.weight": "model-00002-of-00003.safetensors",
250
+ "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
251
+ "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
252
+ "transformer.h.27.ln_2.bias": "model-00002-of-00003.safetensors",
253
+ "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
254
+ "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
255
+ "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
256
+ "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
257
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
258
+ "transformer.h.28.attn.c_attn.bias": "model-00002-of-00003.safetensors",
259
+ "transformer.h.28.attn.c_attn.weight": "model-00002-of-00003.safetensors",
260
+ "transformer.h.28.attn.c_proj.bias": "model-00002-of-00003.safetensors",
261
+ "transformer.h.28.attn.c_proj.weight": "model-00002-of-00003.safetensors",
262
+ "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
263
+ "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
264
+ "transformer.h.28.ln_2.bias": "model-00002-of-00003.safetensors",
265
+ "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
266
+ "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
267
+ "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
268
+ "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
269
+ "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
270
+ "transformer.h.29.attn.c_attn.bias": "model-00003-of-00003.safetensors",
271
+ "transformer.h.29.attn.c_attn.weight": "model-00003-of-00003.safetensors",
272
+ "transformer.h.29.attn.c_proj.bias": "model-00003-of-00003.safetensors",
273
+ "transformer.h.29.attn.c_proj.weight": "model-00003-of-00003.safetensors",
274
+ "transformer.h.29.ln_1.bias": "model-00003-of-00003.safetensors",
275
+ "transformer.h.29.ln_1.weight": "model-00003-of-00003.safetensors",
276
+ "transformer.h.29.ln_2.bias": "model-00003-of-00003.safetensors",
277
+ "transformer.h.29.ln_2.weight": "model-00003-of-00003.safetensors",
278
+ "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
279
+ "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
280
+ "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
281
+ "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
282
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00003.safetensors",
283
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
284
+ "transformer.h.3.attn.c_proj.bias": "model-00001-of-00003.safetensors",
285
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
286
+ "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
287
+ "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
288
+ "transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
289
+ "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
290
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
291
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
292
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
293
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
294
+ "transformer.h.30.attn.c_attn.bias": "model-00003-of-00003.safetensors",
295
+ "transformer.h.30.attn.c_attn.weight": "model-00003-of-00003.safetensors",
296
+ "transformer.h.30.attn.c_proj.bias": "model-00003-of-00003.safetensors",
297
+ "transformer.h.30.attn.c_proj.weight": "model-00003-of-00003.safetensors",
298
+ "transformer.h.30.ln_1.bias": "model-00003-of-00003.safetensors",
299
+ "transformer.h.30.ln_1.weight": "model-00003-of-00003.safetensors",
300
+ "transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
301
+ "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
302
+ "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
303
+ "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
304
+ "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
305
+ "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
306
+ "transformer.h.31.attn.c_attn.bias": "model-00003-of-00003.safetensors",
307
+ "transformer.h.31.attn.c_attn.weight": "model-00003-of-00003.safetensors",
308
+ "transformer.h.31.attn.c_proj.bias": "model-00003-of-00003.safetensors",
309
+ "transformer.h.31.attn.c_proj.weight": "model-00003-of-00003.safetensors",
310
+ "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
311
+ "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
312
+ "transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
313
+ "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
314
+ "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
315
+ "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
316
+ "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
317
+ "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
318
+ "transformer.h.32.attn.c_attn.bias": "model-00003-of-00003.safetensors",
319
+ "transformer.h.32.attn.c_attn.weight": "model-00003-of-00003.safetensors",
320
+ "transformer.h.32.attn.c_proj.bias": "model-00003-of-00003.safetensors",
321
+ "transformer.h.32.attn.c_proj.weight": "model-00003-of-00003.safetensors",
322
+ "transformer.h.32.ln_1.bias": "model-00003-of-00003.safetensors",
323
+ "transformer.h.32.ln_1.weight": "model-00003-of-00003.safetensors",
324
+ "transformer.h.32.ln_2.bias": "model-00003-of-00003.safetensors",
325
+ "transformer.h.32.ln_2.weight": "model-00003-of-00003.safetensors",
326
+ "transformer.h.32.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
327
+ "transformer.h.32.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
328
+ "transformer.h.32.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
329
+ "transformer.h.32.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
330
+ "transformer.h.33.attn.c_attn.bias": "model-00003-of-00003.safetensors",
331
+ "transformer.h.33.attn.c_attn.weight": "model-00003-of-00003.safetensors",
332
+ "transformer.h.33.attn.c_proj.bias": "model-00003-of-00003.safetensors",
333
+ "transformer.h.33.attn.c_proj.weight": "model-00003-of-00003.safetensors",
334
+ "transformer.h.33.ln_1.bias": "model-00003-of-00003.safetensors",
335
+ "transformer.h.33.ln_1.weight": "model-00003-of-00003.safetensors",
336
+ "transformer.h.33.ln_2.bias": "model-00003-of-00003.safetensors",
337
+ "transformer.h.33.ln_2.weight": "model-00003-of-00003.safetensors",
338
+ "transformer.h.33.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
339
+ "transformer.h.33.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
340
+ "transformer.h.33.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
341
+ "transformer.h.33.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
342
+ "transformer.h.34.attn.c_attn.bias": "model-00003-of-00003.safetensors",
343
+ "transformer.h.34.attn.c_attn.weight": "model-00003-of-00003.safetensors",
344
+ "transformer.h.34.attn.c_proj.bias": "model-00003-of-00003.safetensors",
345
+ "transformer.h.34.attn.c_proj.weight": "model-00003-of-00003.safetensors",
346
+ "transformer.h.34.ln_1.bias": "model-00003-of-00003.safetensors",
347
+ "transformer.h.34.ln_1.weight": "model-00003-of-00003.safetensors",
348
+ "transformer.h.34.ln_2.bias": "model-00003-of-00003.safetensors",
349
+ "transformer.h.34.ln_2.weight": "model-00003-of-00003.safetensors",
350
+ "transformer.h.34.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
351
+ "transformer.h.34.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
352
+ "transformer.h.34.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
353
+ "transformer.h.34.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
354
+ "transformer.h.35.attn.c_attn.bias": "model-00003-of-00003.safetensors",
355
+ "transformer.h.35.attn.c_attn.weight": "model-00003-of-00003.safetensors",
356
+ "transformer.h.35.attn.c_proj.bias": "model-00003-of-00003.safetensors",
357
+ "transformer.h.35.attn.c_proj.weight": "model-00003-of-00003.safetensors",
358
+ "transformer.h.35.ln_1.bias": "model-00003-of-00003.safetensors",
359
+ "transformer.h.35.ln_1.weight": "model-00003-of-00003.safetensors",
360
+ "transformer.h.35.ln_2.bias": "model-00003-of-00003.safetensors",
361
+ "transformer.h.35.ln_2.weight": "model-00003-of-00003.safetensors",
362
+ "transformer.h.35.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
363
+ "transformer.h.35.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
364
+ "transformer.h.35.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
365
+ "transformer.h.35.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
366
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00003.safetensors",
367
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
368
+ "transformer.h.4.attn.c_proj.bias": "model-00001-of-00003.safetensors",
369
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
370
+ "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
371
+ "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
372
+ "transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
373
+ "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
374
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
375
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
376
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
377
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
378
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00003.safetensors",
379
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
380
+ "transformer.h.5.attn.c_proj.bias": "model-00001-of-00003.safetensors",
381
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
382
+ "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
383
+ "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
384
+ "transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
385
+ "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
386
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
387
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
388
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
389
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
390
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00003.safetensors",
391
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
392
+ "transformer.h.6.attn.c_proj.bias": "model-00001-of-00003.safetensors",
393
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
394
+ "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
395
+ "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
396
+ "transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
397
+ "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
398
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
399
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
400
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
401
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
402
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00003.safetensors",
403
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
404
+ "transformer.h.7.attn.c_proj.bias": "model-00001-of-00003.safetensors",
405
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
406
+ "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
407
+ "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
408
+ "transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
409
+ "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
410
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
411
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
412
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
413
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
414
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00003.safetensors",
415
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
416
+ "transformer.h.8.attn.c_proj.bias": "model-00001-of-00003.safetensors",
417
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
418
+ "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
419
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
420
+ "transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
421
+ "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
422
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
423
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
424
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
425
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
426
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00003.safetensors",
427
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
428
+ "transformer.h.9.attn.c_proj.bias": "model-00001-of-00003.safetensors",
429
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
430
+ "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
431
+ "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
432
+ "transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
433
+ "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
434
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
435
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
436
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
437
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
438
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
439
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
440
+ "transformer.wpe.weight": "model-00001-of-00003.safetensors",
441
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
442
+ }
443
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": "<|endoftext|>",
38
+ "unk_token": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "clean_up_tokenization_spaces": true,
180
+ "eos_token": "<|endoftext|>",
181
+ "model_max_length": 1000000000000000019884624838656,
182
+ "pad_token": "<|endoftext|>",
183
+ "tokenizer_class": "GPT2Tokenizer",
184
+ "unk_token": "<|endoftext|>",
185
+ "vocab_size": 49152
186
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192787e14650e9dcc746872c8d4a95db39ed2c8922634f85b71f7731eea75da5
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff