philschmid HF staff commited on
Commit
a745926
1 Parent(s): 2ecbe93

push sharded model

Browse files
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codegen-6B-mono",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "CodeGenForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "codegen",
15
+ "n_ctx": 2048,
16
+ "n_embd": 4096,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 33,
20
+ "n_positions": 2048,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 64,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.21.2",
40
+ "use_cache": true,
41
+ "vocab_size": 51200
42
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model-00001-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78690c436cde1202149745f07b03dd30f2f8467f501dd3d121050dbadc3cfce3
3
+ size 964767864
pytorch_model-00002-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65782447c4722f98bd2f7005bc6f24f747985d7be743dbd2517edcc86e742da3
3
+ size 948065769
pytorch_model-00003-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e146ecdcc5d9bc3fbf9c7deee3046a812c33aeffbd44bf729c656adabad9f081
3
+ size 952252768
pytorch_model-00004-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7247d022679a6fc0b95a5b1ff6726b92fa012008c052a7bd99019f26779eb9fb
3
+ size 948033065
pytorch_model-00005-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da32a0783f1096260da8eea2a36d83cbb41d47f21105d86a19add799f97b6c4c
3
+ size 948065769
pytorch_model-00006-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22a34b595e01f294ac13a94db2e7b306f2e666f8d5f495b01929aa14c287e31
3
+ size 952252768
pytorch_model-00007-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d78f44b5986a776f14be34b513517b560c489697a0d93bbb1e476fa0970b6ea
3
+ size 948033065
pytorch_model-00008-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251c14531411b098f52b50441356e6da13d5e45b6b14aa8701777b769e6b53aa
3
+ size 948065833
pytorch_model-00009-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1eef861d2243a34d1b19d8f1384f95bb8da54443989057dcc3eea3743e3bc22
3
+ size 952252768
pytorch_model-00010-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:508cb1cf56184d1a172e243c418e890ffcbc89c4d9fc0bed3c0c1dcd8c5de219
3
+ size 948033065
pytorch_model-00011-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6b2166428e5fb3fa639f0350fc79b428c8f0c438d10a4a73710b4179118f1f
3
+ size 948065833
pytorch_model-00012-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7499c4c048c3b9d2fac981125e26d04655fac2e14a6faeb62c6b68457be112
3
+ size 952252768
pytorch_model-00013-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802fd4213a9b114088911b240e7a95dceed5d9c14bdd6840a0d4aefba9922a92
3
+ size 948033065
pytorch_model-00014-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a3c23c31134c6fc650a0bbae88332ab45f3e0047b7ba462d10c7082cb574d3
3
+ size 948065833
pytorch_model-00015-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede106f4864b6b7f03f3d32ad03133a3ed07cbc7a677b22a223741b243be72e7
3
+ size 960684088
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14266839040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00015-of-00015.bin",
7
+ "lm_head.weight": "pytorch_model-00015-of-00015.bin",
8
+ "transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00015.bin",
9
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00015.bin",
10
+ "transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00015.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00015.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00015.bin",
13
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00015.bin",
14
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00015.bin",
15
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00015.bin",
16
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00015.bin",
17
+ "transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00015.bin",
18
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00015.bin",
19
+ "transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00015.bin",
20
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00015.bin",
21
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00015.bin",
22
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00002-of-00015.bin",
23
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00002-of-00015.bin",
24
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00002-of-00015.bin",
25
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00002-of-00015.bin",
26
+ "transformer.h.10.attn.causal_mask": "pytorch_model-00005-of-00015.bin",
27
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00005-of-00015.bin",
28
+ "transformer.h.10.attn.qkv_proj.weight": "pytorch_model-00005-of-00015.bin",
29
+ "transformer.h.10.ln_1.bias": "pytorch_model-00005-of-00015.bin",
30
+ "transformer.h.10.ln_1.weight": "pytorch_model-00005-of-00015.bin",
31
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00005-of-00015.bin",
32
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00005-of-00015.bin",
33
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00006-of-00015.bin",
34
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00006-of-00015.bin",
35
+ "transformer.h.11.attn.causal_mask": "pytorch_model-00006-of-00015.bin",
36
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00006-of-00015.bin",
37
+ "transformer.h.11.attn.qkv_proj.weight": "pytorch_model-00006-of-00015.bin",
38
+ "transformer.h.11.ln_1.bias": "pytorch_model-00006-of-00015.bin",
39
+ "transformer.h.11.ln_1.weight": "pytorch_model-00006-of-00015.bin",
40
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00006-of-00015.bin",
41
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00006-of-00015.bin",
42
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00006-of-00015.bin",
43
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00006-of-00015.bin",
44
+ "transformer.h.12.attn.causal_mask": "pytorch_model-00006-of-00015.bin",
45
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00006-of-00015.bin",
46
+ "transformer.h.12.attn.qkv_proj.weight": "pytorch_model-00006-of-00015.bin",
47
+ "transformer.h.12.ln_1.bias": "pytorch_model-00006-of-00015.bin",
48
+ "transformer.h.12.ln_1.weight": "pytorch_model-00006-of-00015.bin",
49
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00006-of-00015.bin",
50
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00006-of-00015.bin",
51
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00006-of-00015.bin",
52
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00006-of-00015.bin",
53
+ "transformer.h.13.attn.causal_mask": "pytorch_model-00006-of-00015.bin",
54
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00007-of-00015.bin",
55
+ "transformer.h.13.attn.qkv_proj.weight": "pytorch_model-00007-of-00015.bin",
56
+ "transformer.h.13.ln_1.bias": "pytorch_model-00006-of-00015.bin",
57
+ "transformer.h.13.ln_1.weight": "pytorch_model-00006-of-00015.bin",
58
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00007-of-00015.bin",
59
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00007-of-00015.bin",
60
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00007-of-00015.bin",
61
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00007-of-00015.bin",
62
+ "transformer.h.14.attn.causal_mask": "pytorch_model-00007-of-00015.bin",
63
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00007-of-00015.bin",
64
+ "transformer.h.14.attn.qkv_proj.weight": "pytorch_model-00007-of-00015.bin",
65
+ "transformer.h.14.ln_1.bias": "pytorch_model-00007-of-00015.bin",
66
+ "transformer.h.14.ln_1.weight": "pytorch_model-00007-of-00015.bin",
67
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00007-of-00015.bin",
68
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00007-of-00015.bin",
69
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00007-of-00015.bin",
70
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00007-of-00015.bin",
71
+ "transformer.h.15.attn.causal_mask": "pytorch_model-00007-of-00015.bin",
72
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00007-of-00015.bin",
73
+ "transformer.h.15.attn.qkv_proj.weight": "pytorch_model-00007-of-00015.bin",
74
+ "transformer.h.15.ln_1.bias": "pytorch_model-00007-of-00015.bin",
75
+ "transformer.h.15.ln_1.weight": "pytorch_model-00007-of-00015.bin",
76
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00008-of-00015.bin",
77
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00008-of-00015.bin",
78
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00008-of-00015.bin",
79
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00008-of-00015.bin",
80
+ "transformer.h.16.attn.causal_mask": "pytorch_model-00008-of-00015.bin",
81
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00008-of-00015.bin",
82
+ "transformer.h.16.attn.qkv_proj.weight": "pytorch_model-00008-of-00015.bin",
83
+ "transformer.h.16.ln_1.bias": "pytorch_model-00008-of-00015.bin",
84
+ "transformer.h.16.ln_1.weight": "pytorch_model-00008-of-00015.bin",
85
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00008-of-00015.bin",
86
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00008-of-00015.bin",
87
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00008-of-00015.bin",
88
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00008-of-00015.bin",
89
+ "transformer.h.17.attn.causal_mask": "pytorch_model-00008-of-00015.bin",
90
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00008-of-00015.bin",
91
+ "transformer.h.17.attn.qkv_proj.weight": "pytorch_model-00008-of-00015.bin",
92
+ "transformer.h.17.ln_1.bias": "pytorch_model-00008-of-00015.bin",
93
+ "transformer.h.17.ln_1.weight": "pytorch_model-00008-of-00015.bin",
94
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00008-of-00015.bin",
95
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00008-of-00015.bin",
96
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00009-of-00015.bin",
97
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00009-of-00015.bin",
98
+ "transformer.h.18.attn.causal_mask": "pytorch_model-00009-of-00015.bin",
99
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00009-of-00015.bin",
100
+ "transformer.h.18.attn.qkv_proj.weight": "pytorch_model-00009-of-00015.bin",
101
+ "transformer.h.18.ln_1.bias": "pytorch_model-00009-of-00015.bin",
102
+ "transformer.h.18.ln_1.weight": "pytorch_model-00009-of-00015.bin",
103
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00009-of-00015.bin",
104
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00009-of-00015.bin",
105
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00009-of-00015.bin",
106
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00009-of-00015.bin",
107
+ "transformer.h.19.attn.causal_mask": "pytorch_model-00009-of-00015.bin",
108
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00009-of-00015.bin",
109
+ "transformer.h.19.attn.qkv_proj.weight": "pytorch_model-00009-of-00015.bin",
110
+ "transformer.h.19.ln_1.bias": "pytorch_model-00009-of-00015.bin",
111
+ "transformer.h.19.ln_1.weight": "pytorch_model-00009-of-00015.bin",
112
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00009-of-00015.bin",
113
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00009-of-00015.bin",
114
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00009-of-00015.bin",
115
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00009-of-00015.bin",
116
+ "transformer.h.2.attn.causal_mask": "pytorch_model-00002-of-00015.bin",
117
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00002-of-00015.bin",
118
+ "transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00002-of-00015.bin",
119
+ "transformer.h.2.ln_1.bias": "pytorch_model-00002-of-00015.bin",
120
+ "transformer.h.2.ln_1.weight": "pytorch_model-00002-of-00015.bin",
121
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00002-of-00015.bin",
122
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00002-of-00015.bin",
123
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00002-of-00015.bin",
124
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00002-of-00015.bin",
125
+ "transformer.h.20.attn.causal_mask": "pytorch_model-00009-of-00015.bin",
126
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00010-of-00015.bin",
127
+ "transformer.h.20.attn.qkv_proj.weight": "pytorch_model-00010-of-00015.bin",
128
+ "transformer.h.20.ln_1.bias": "pytorch_model-00009-of-00015.bin",
129
+ "transformer.h.20.ln_1.weight": "pytorch_model-00009-of-00015.bin",
130
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00010-of-00015.bin",
131
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00010-of-00015.bin",
132
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00010-of-00015.bin",
133
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00010-of-00015.bin",
134
+ "transformer.h.21.attn.causal_mask": "pytorch_model-00010-of-00015.bin",
135
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00010-of-00015.bin",
136
+ "transformer.h.21.attn.qkv_proj.weight": "pytorch_model-00010-of-00015.bin",
137
+ "transformer.h.21.ln_1.bias": "pytorch_model-00010-of-00015.bin",
138
+ "transformer.h.21.ln_1.weight": "pytorch_model-00010-of-00015.bin",
139
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00010-of-00015.bin",
140
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00010-of-00015.bin",
141
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00010-of-00015.bin",
142
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00010-of-00015.bin",
143
+ "transformer.h.22.attn.causal_mask": "pytorch_model-00010-of-00015.bin",
144
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00010-of-00015.bin",
145
+ "transformer.h.22.attn.qkv_proj.weight": "pytorch_model-00010-of-00015.bin",
146
+ "transformer.h.22.ln_1.bias": "pytorch_model-00010-of-00015.bin",
147
+ "transformer.h.22.ln_1.weight": "pytorch_model-00010-of-00015.bin",
148
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00011-of-00015.bin",
149
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00011-of-00015.bin",
150
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00011-of-00015.bin",
151
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00011-of-00015.bin",
152
+ "transformer.h.23.attn.causal_mask": "pytorch_model-00011-of-00015.bin",
153
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00011-of-00015.bin",
154
+ "transformer.h.23.attn.qkv_proj.weight": "pytorch_model-00011-of-00015.bin",
155
+ "transformer.h.23.ln_1.bias": "pytorch_model-00011-of-00015.bin",
156
+ "transformer.h.23.ln_1.weight": "pytorch_model-00011-of-00015.bin",
157
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00011-of-00015.bin",
158
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00011-of-00015.bin",
159
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00011-of-00015.bin",
160
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00011-of-00015.bin",
161
+ "transformer.h.24.attn.causal_mask": "pytorch_model-00011-of-00015.bin",
162
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00011-of-00015.bin",
163
+ "transformer.h.24.attn.qkv_proj.weight": "pytorch_model-00011-of-00015.bin",
164
+ "transformer.h.24.ln_1.bias": "pytorch_model-00011-of-00015.bin",
165
+ "transformer.h.24.ln_1.weight": "pytorch_model-00011-of-00015.bin",
166
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00011-of-00015.bin",
167
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00011-of-00015.bin",
168
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00012-of-00015.bin",
169
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00012-of-00015.bin",
170
+ "transformer.h.25.attn.causal_mask": "pytorch_model-00012-of-00015.bin",
171
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00012-of-00015.bin",
172
+ "transformer.h.25.attn.qkv_proj.weight": "pytorch_model-00012-of-00015.bin",
173
+ "transformer.h.25.ln_1.bias": "pytorch_model-00012-of-00015.bin",
174
+ "transformer.h.25.ln_1.weight": "pytorch_model-00012-of-00015.bin",
175
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00012-of-00015.bin",
176
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00012-of-00015.bin",
177
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00012-of-00015.bin",
178
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00012-of-00015.bin",
179
+ "transformer.h.26.attn.causal_mask": "pytorch_model-00012-of-00015.bin",
180
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00012-of-00015.bin",
181
+ "transformer.h.26.attn.qkv_proj.weight": "pytorch_model-00012-of-00015.bin",
182
+ "transformer.h.26.ln_1.bias": "pytorch_model-00012-of-00015.bin",
183
+ "transformer.h.26.ln_1.weight": "pytorch_model-00012-of-00015.bin",
184
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00012-of-00015.bin",
185
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00012-of-00015.bin",
186
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00012-of-00015.bin",
187
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00012-of-00015.bin",
188
+ "transformer.h.27.attn.causal_mask": "pytorch_model-00012-of-00015.bin",
189
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00013-of-00015.bin",
190
+ "transformer.h.27.attn.qkv_proj.weight": "pytorch_model-00013-of-00015.bin",
191
+ "transformer.h.27.ln_1.bias": "pytorch_model-00012-of-00015.bin",
192
+ "transformer.h.27.ln_1.weight": "pytorch_model-00012-of-00015.bin",
193
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00013-of-00015.bin",
194
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00013-of-00015.bin",
195
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00013-of-00015.bin",
196
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00013-of-00015.bin",
197
+ "transformer.h.28.attn.causal_mask": "pytorch_model-00013-of-00015.bin",
198
+ "transformer.h.28.attn.out_proj.weight": "pytorch_model-00013-of-00015.bin",
199
+ "transformer.h.28.attn.qkv_proj.weight": "pytorch_model-00013-of-00015.bin",
200
+ "transformer.h.28.ln_1.bias": "pytorch_model-00013-of-00015.bin",
201
+ "transformer.h.28.ln_1.weight": "pytorch_model-00013-of-00015.bin",
202
+ "transformer.h.28.mlp.fc_in.bias": "pytorch_model-00013-of-00015.bin",
203
+ "transformer.h.28.mlp.fc_in.weight": "pytorch_model-00013-of-00015.bin",
204
+ "transformer.h.28.mlp.fc_out.bias": "pytorch_model-00013-of-00015.bin",
205
+ "transformer.h.28.mlp.fc_out.weight": "pytorch_model-00013-of-00015.bin",
206
+ "transformer.h.29.attn.causal_mask": "pytorch_model-00013-of-00015.bin",
207
+ "transformer.h.29.attn.out_proj.weight": "pytorch_model-00013-of-00015.bin",
208
+ "transformer.h.29.attn.qkv_proj.weight": "pytorch_model-00013-of-00015.bin",
209
+ "transformer.h.29.ln_1.bias": "pytorch_model-00013-of-00015.bin",
210
+ "transformer.h.29.ln_1.weight": "pytorch_model-00013-of-00015.bin",
211
+ "transformer.h.29.mlp.fc_in.bias": "pytorch_model-00014-of-00015.bin",
212
+ "transformer.h.29.mlp.fc_in.weight": "pytorch_model-00014-of-00015.bin",
213
+ "transformer.h.29.mlp.fc_out.bias": "pytorch_model-00014-of-00015.bin",
214
+ "transformer.h.29.mlp.fc_out.weight": "pytorch_model-00014-of-00015.bin",
215
+ "transformer.h.3.attn.causal_mask": "pytorch_model-00002-of-00015.bin",
216
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00002-of-00015.bin",
217
+ "transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00002-of-00015.bin",
218
+ "transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00015.bin",
219
+ "transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00015.bin",
220
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00002-of-00015.bin",
221
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00002-of-00015.bin",
222
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00003-of-00015.bin",
223
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00003-of-00015.bin",
224
+ "transformer.h.30.attn.causal_mask": "pytorch_model-00014-of-00015.bin",
225
+ "transformer.h.30.attn.out_proj.weight": "pytorch_model-00014-of-00015.bin",
226
+ "transformer.h.30.attn.qkv_proj.weight": "pytorch_model-00014-of-00015.bin",
227
+ "transformer.h.30.ln_1.bias": "pytorch_model-00014-of-00015.bin",
228
+ "transformer.h.30.ln_1.weight": "pytorch_model-00014-of-00015.bin",
229
+ "transformer.h.30.mlp.fc_in.bias": "pytorch_model-00014-of-00015.bin",
230
+ "transformer.h.30.mlp.fc_in.weight": "pytorch_model-00014-of-00015.bin",
231
+ "transformer.h.30.mlp.fc_out.bias": "pytorch_model-00014-of-00015.bin",
232
+ "transformer.h.30.mlp.fc_out.weight": "pytorch_model-00014-of-00015.bin",
233
+ "transformer.h.31.attn.causal_mask": "pytorch_model-00014-of-00015.bin",
234
+ "transformer.h.31.attn.out_proj.weight": "pytorch_model-00014-of-00015.bin",
235
+ "transformer.h.31.attn.qkv_proj.weight": "pytorch_model-00014-of-00015.bin",
236
+ "transformer.h.31.ln_1.bias": "pytorch_model-00014-of-00015.bin",
237
+ "transformer.h.31.ln_1.weight": "pytorch_model-00014-of-00015.bin",
238
+ "transformer.h.31.mlp.fc_in.bias": "pytorch_model-00014-of-00015.bin",
239
+ "transformer.h.31.mlp.fc_in.weight": "pytorch_model-00014-of-00015.bin",
240
+ "transformer.h.31.mlp.fc_out.bias": "pytorch_model-00015-of-00015.bin",
241
+ "transformer.h.31.mlp.fc_out.weight": "pytorch_model-00015-of-00015.bin",
242
+ "transformer.h.32.attn.causal_mask": "pytorch_model-00015-of-00015.bin",
243
+ "transformer.h.32.attn.out_proj.weight": "pytorch_model-00015-of-00015.bin",
244
+ "transformer.h.32.attn.qkv_proj.weight": "pytorch_model-00015-of-00015.bin",
245
+ "transformer.h.32.ln_1.bias": "pytorch_model-00015-of-00015.bin",
246
+ "transformer.h.32.ln_1.weight": "pytorch_model-00015-of-00015.bin",
247
+ "transformer.h.32.mlp.fc_in.bias": "pytorch_model-00015-of-00015.bin",
248
+ "transformer.h.32.mlp.fc_in.weight": "pytorch_model-00015-of-00015.bin",
249
+ "transformer.h.32.mlp.fc_out.bias": "pytorch_model-00015-of-00015.bin",
250
+ "transformer.h.32.mlp.fc_out.weight": "pytorch_model-00015-of-00015.bin",
251
+ "transformer.h.4.attn.causal_mask": "pytorch_model-00003-of-00015.bin",
252
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00003-of-00015.bin",
253
+ "transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00003-of-00015.bin",
254
+ "transformer.h.4.ln_1.bias": "pytorch_model-00003-of-00015.bin",
255
+ "transformer.h.4.ln_1.weight": "pytorch_model-00003-of-00015.bin",
256
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00003-of-00015.bin",
257
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00003-of-00015.bin",
258
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00003-of-00015.bin",
259
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00003-of-00015.bin",
260
+ "transformer.h.5.attn.causal_mask": "pytorch_model-00003-of-00015.bin",
261
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00003-of-00015.bin",
262
+ "transformer.h.5.attn.qkv_proj.weight": "pytorch_model-00003-of-00015.bin",
263
+ "transformer.h.5.ln_1.bias": "pytorch_model-00003-of-00015.bin",
264
+ "transformer.h.5.ln_1.weight": "pytorch_model-00003-of-00015.bin",
265
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00003-of-00015.bin",
266
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00003-of-00015.bin",
267
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00003-of-00015.bin",
268
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00003-of-00015.bin",
269
+ "transformer.h.6.attn.causal_mask": "pytorch_model-00003-of-00015.bin",
270
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00004-of-00015.bin",
271
+ "transformer.h.6.attn.qkv_proj.weight": "pytorch_model-00004-of-00015.bin",
272
+ "transformer.h.6.ln_1.bias": "pytorch_model-00003-of-00015.bin",
273
+ "transformer.h.6.ln_1.weight": "pytorch_model-00003-of-00015.bin",
274
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00004-of-00015.bin",
275
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00004-of-00015.bin",
276
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00004-of-00015.bin",
277
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00004-of-00015.bin",
278
+ "transformer.h.7.attn.causal_mask": "pytorch_model-00004-of-00015.bin",
279
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00004-of-00015.bin",
280
+ "transformer.h.7.attn.qkv_proj.weight": "pytorch_model-00004-of-00015.bin",
281
+ "transformer.h.7.ln_1.bias": "pytorch_model-00004-of-00015.bin",
282
+ "transformer.h.7.ln_1.weight": "pytorch_model-00004-of-00015.bin",
283
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00004-of-00015.bin",
284
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00004-of-00015.bin",
285
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00004-of-00015.bin",
286
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00004-of-00015.bin",
287
+ "transformer.h.8.attn.causal_mask": "pytorch_model-00004-of-00015.bin",
288
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00004-of-00015.bin",
289
+ "transformer.h.8.attn.qkv_proj.weight": "pytorch_model-00004-of-00015.bin",
290
+ "transformer.h.8.ln_1.bias": "pytorch_model-00004-of-00015.bin",
291
+ "transformer.h.8.ln_1.weight": "pytorch_model-00004-of-00015.bin",
292
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00005-of-00015.bin",
293
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00005-of-00015.bin",
294
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00005-of-00015.bin",
295
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00005-of-00015.bin",
296
+ "transformer.h.9.attn.causal_mask": "pytorch_model-00005-of-00015.bin",
297
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00005-of-00015.bin",
298
+ "transformer.h.9.attn.qkv_proj.weight": "pytorch_model-00005-of-00015.bin",
299
+ "transformer.h.9.ln_1.bias": "pytorch_model-00005-of-00015.bin",
300
+ "transformer.h.9.ln_1.weight": "pytorch_model-00005-of-00015.bin",
301
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00005-of-00015.bin",
302
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00005-of-00015.bin",
303
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00005-of-00015.bin",
304
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00005-of-00015.bin",
305
+ "transformer.ln_f.bias": "pytorch_model-00015-of-00015.bin",
306
+ "transformer.ln_f.weight": "pytorch_model-00015-of-00015.bin",
307
+ "transformer.wte.weight": "pytorch_model-00001-of-00015.bin"
308
+ }
309
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1e+20,
6
+ "name_or_path": "Salesforce/codegen-6B-mono",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "CodeGenTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff