Jangmin Oh commited on
Commit
6955be1
1 Parent(s): 7988e46

commit the fine-tuned by PEFT and merged model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ midm_bitext_tokenizer.model filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 3,
3
+ "<pad>": 0,
4
+ "<s>": 2,
5
+ "<unk>": 1
6
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "KT-AI/midm-bitext-S-7B-inst-v1",
3
+ "activation_function": "silu",
4
+ "architectures": [
5
+ "MidmLMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "KT-AI/midm-bitext-S-7B-inst-v1--configuration_midm.MidmBitextConfig",
10
+ "AutoModelForCausalLM": "KT-AI/midm-bitext-S-7B-inst-v1--modeling_midm.MidmLMHeadModel"
11
+ },
12
+ "bos_token_id": 2,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 3,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "model_type": "midm-bitext-S",
18
+ "n_embd": 4096,
19
+ "n_head": 32,
20
+ "n_inner": 10880,
21
+ "n_layer": 32,
22
+ "n_positions": 8192,
23
+ "normalization_type": "layernorm1p",
24
+ "pad_token_id": 0,
25
+ "reorder_and_upcast_attn": false,
26
+ "resid_pdrop": 0.0,
27
+ "rotary_percentage": 0.5,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "scale_qk_by_inverse_layer_idx": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.35.0.dev0",
39
+ "use_absolute_position_embedding": false,
40
+ "use_cache": true,
41
+ "use_rotary_position_embedding": true,
42
+ "vocab_size": 72192
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.35.0.dev0"
7
+ }
midm_bitext_tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98789fa1bf89a1f9692889fb4a0029d3d096a9109cebf4f6bce1a255f2701378
3
+ size 1457356
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b031639710ff392c8ee143e7553b6e6731fc0fb4d45092bb6f114f39a2b4f98
3
+ size 3939753936
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a10700700933289af5ad5e1e5e92e8c4a9e089224000eddc549159cb6317fc
3
+ size 3884212992
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edc2f617f9a544e6879dcd1333eb6225ff0b37cfcbcb271a00ca1108a715025
3
+ size 3928236520
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e56eec9983edd65e9866eb0b1e569e935d60e2a1efd6d6d5d0900daa4b2fa1d
3
+ size 3839124128
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ccba75ce22542fe5f77348eae115b553079ff5fd3edbf65d305044cac48b53
3
+ size 591396992
model.safetensors.index.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16182689984
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "transformer.h.0.attn.bias": "model-00001-of-00005.safetensors",
8
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00005.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00005.safetensors",
10
+ "transformer.h.0.attn.masked_bias": "model-00001-of-00005.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00005.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00005.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00005.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00005.safetensors",
15
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
16
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
17
+ "transformer.h.1.attn.bias": "model-00001-of-00005.safetensors",
18
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00005.safetensors",
19
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00005.safetensors",
20
+ "transformer.h.1.attn.masked_bias": "model-00001-of-00005.safetensors",
21
+ "transformer.h.1.ln_1.bias": "model-00001-of-00005.safetensors",
22
+ "transformer.h.1.ln_1.weight": "model-00001-of-00005.safetensors",
23
+ "transformer.h.1.ln_2.bias": "model-00001-of-00005.safetensors",
24
+ "transformer.h.1.ln_2.weight": "model-00001-of-00005.safetensors",
25
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
26
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
27
+ "transformer.h.10.attn.bias": "model-00002-of-00005.safetensors",
28
+ "transformer.h.10.attn.c_attn.weight": "model-00002-of-00005.safetensors",
29
+ "transformer.h.10.attn.c_proj.weight": "model-00002-of-00005.safetensors",
30
+ "transformer.h.10.attn.masked_bias": "model-00002-of-00005.safetensors",
31
+ "transformer.h.10.ln_1.bias": "model-00002-of-00005.safetensors",
32
+ "transformer.h.10.ln_1.weight": "model-00002-of-00005.safetensors",
33
+ "transformer.h.10.ln_2.bias": "model-00002-of-00005.safetensors",
34
+ "transformer.h.10.ln_2.weight": "model-00002-of-00005.safetensors",
35
+ "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
36
+ "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
37
+ "transformer.h.11.attn.bias": "model-00002-of-00005.safetensors",
38
+ "transformer.h.11.attn.c_attn.weight": "model-00002-of-00005.safetensors",
39
+ "transformer.h.11.attn.c_proj.weight": "model-00002-of-00005.safetensors",
40
+ "transformer.h.11.attn.masked_bias": "model-00002-of-00005.safetensors",
41
+ "transformer.h.11.ln_1.bias": "model-00002-of-00005.safetensors",
42
+ "transformer.h.11.ln_1.weight": "model-00002-of-00005.safetensors",
43
+ "transformer.h.11.ln_2.bias": "model-00002-of-00005.safetensors",
44
+ "transformer.h.11.ln_2.weight": "model-00002-of-00005.safetensors",
45
+ "transformer.h.11.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
46
+ "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
47
+ "transformer.h.12.attn.bias": "model-00002-of-00005.safetensors",
48
+ "transformer.h.12.attn.c_attn.weight": "model-00002-of-00005.safetensors",
49
+ "transformer.h.12.attn.c_proj.weight": "model-00002-of-00005.safetensors",
50
+ "transformer.h.12.attn.masked_bias": "model-00002-of-00005.safetensors",
51
+ "transformer.h.12.ln_1.bias": "model-00002-of-00005.safetensors",
52
+ "transformer.h.12.ln_1.weight": "model-00002-of-00005.safetensors",
53
+ "transformer.h.12.ln_2.bias": "model-00002-of-00005.safetensors",
54
+ "transformer.h.12.ln_2.weight": "model-00002-of-00005.safetensors",
55
+ "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
56
+ "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
57
+ "transformer.h.13.attn.bias": "model-00002-of-00005.safetensors",
58
+ "transformer.h.13.attn.c_attn.weight": "model-00002-of-00005.safetensors",
59
+ "transformer.h.13.attn.c_proj.weight": "model-00002-of-00005.safetensors",
60
+ "transformer.h.13.attn.masked_bias": "model-00002-of-00005.safetensors",
61
+ "transformer.h.13.ln_1.bias": "model-00002-of-00005.safetensors",
62
+ "transformer.h.13.ln_1.weight": "model-00002-of-00005.safetensors",
63
+ "transformer.h.13.ln_2.bias": "model-00002-of-00005.safetensors",
64
+ "transformer.h.13.ln_2.weight": "model-00002-of-00005.safetensors",
65
+ "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
66
+ "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
67
+ "transformer.h.14.attn.bias": "model-00002-of-00005.safetensors",
68
+ "transformer.h.14.attn.c_attn.weight": "model-00002-of-00005.safetensors",
69
+ "transformer.h.14.attn.c_proj.weight": "model-00002-of-00005.safetensors",
70
+ "transformer.h.14.attn.masked_bias": "model-00002-of-00005.safetensors",
71
+ "transformer.h.14.ln_1.bias": "model-00002-of-00005.safetensors",
72
+ "transformer.h.14.ln_1.weight": "model-00002-of-00005.safetensors",
73
+ "transformer.h.14.ln_2.bias": "model-00002-of-00005.safetensors",
74
+ "transformer.h.14.ln_2.weight": "model-00002-of-00005.safetensors",
75
+ "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
76
+ "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
77
+ "transformer.h.15.attn.bias": "model-00002-of-00005.safetensors",
78
+ "transformer.h.15.attn.c_attn.weight": "model-00002-of-00005.safetensors",
79
+ "transformer.h.15.attn.c_proj.weight": "model-00002-of-00005.safetensors",
80
+ "transformer.h.15.attn.masked_bias": "model-00002-of-00005.safetensors",
81
+ "transformer.h.15.ln_1.bias": "model-00002-of-00005.safetensors",
82
+ "transformer.h.15.ln_1.weight": "model-00002-of-00005.safetensors",
83
+ "transformer.h.15.ln_2.bias": "model-00002-of-00005.safetensors",
84
+ "transformer.h.15.ln_2.weight": "model-00002-of-00005.safetensors",
85
+ "transformer.h.15.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
86
+ "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
87
+ "transformer.h.16.attn.bias": "model-00003-of-00005.safetensors",
88
+ "transformer.h.16.attn.c_attn.weight": "model-00003-of-00005.safetensors",
89
+ "transformer.h.16.attn.c_proj.weight": "model-00003-of-00005.safetensors",
90
+ "transformer.h.16.attn.masked_bias": "model-00003-of-00005.safetensors",
91
+ "transformer.h.16.ln_1.bias": "model-00003-of-00005.safetensors",
92
+ "transformer.h.16.ln_1.weight": "model-00003-of-00005.safetensors",
93
+ "transformer.h.16.ln_2.bias": "model-00003-of-00005.safetensors",
94
+ "transformer.h.16.ln_2.weight": "model-00003-of-00005.safetensors",
95
+ "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
96
+ "transformer.h.16.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
97
+ "transformer.h.17.attn.bias": "model-00003-of-00005.safetensors",
98
+ "transformer.h.17.attn.c_attn.weight": "model-00003-of-00005.safetensors",
99
+ "transformer.h.17.attn.c_proj.weight": "model-00003-of-00005.safetensors",
100
+ "transformer.h.17.attn.masked_bias": "model-00003-of-00005.safetensors",
101
+ "transformer.h.17.ln_1.bias": "model-00003-of-00005.safetensors",
102
+ "transformer.h.17.ln_1.weight": "model-00003-of-00005.safetensors",
103
+ "transformer.h.17.ln_2.bias": "model-00003-of-00005.safetensors",
104
+ "transformer.h.17.ln_2.weight": "model-00003-of-00005.safetensors",
105
+ "transformer.h.17.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
106
+ "transformer.h.17.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
107
+ "transformer.h.18.attn.bias": "model-00003-of-00005.safetensors",
108
+ "transformer.h.18.attn.c_attn.weight": "model-00003-of-00005.safetensors",
109
+ "transformer.h.18.attn.c_proj.weight": "model-00003-of-00005.safetensors",
110
+ "transformer.h.18.attn.masked_bias": "model-00003-of-00005.safetensors",
111
+ "transformer.h.18.ln_1.bias": "model-00003-of-00005.safetensors",
112
+ "transformer.h.18.ln_1.weight": "model-00003-of-00005.safetensors",
113
+ "transformer.h.18.ln_2.bias": "model-00003-of-00005.safetensors",
114
+ "transformer.h.18.ln_2.weight": "model-00003-of-00005.safetensors",
115
+ "transformer.h.18.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
116
+ "transformer.h.18.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
117
+ "transformer.h.19.attn.bias": "model-00003-of-00005.safetensors",
118
+ "transformer.h.19.attn.c_attn.weight": "model-00003-of-00005.safetensors",
119
+ "transformer.h.19.attn.c_proj.weight": "model-00003-of-00005.safetensors",
120
+ "transformer.h.19.attn.masked_bias": "model-00003-of-00005.safetensors",
121
+ "transformer.h.19.ln_1.bias": "model-00003-of-00005.safetensors",
122
+ "transformer.h.19.ln_1.weight": "model-00003-of-00005.safetensors",
123
+ "transformer.h.19.ln_2.bias": "model-00003-of-00005.safetensors",
124
+ "transformer.h.19.ln_2.weight": "model-00003-of-00005.safetensors",
125
+ "transformer.h.19.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
126
+ "transformer.h.19.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
127
+ "transformer.h.2.attn.bias": "model-00001-of-00005.safetensors",
128
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00005.safetensors",
129
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00005.safetensors",
130
+ "transformer.h.2.attn.masked_bias": "model-00001-of-00005.safetensors",
131
+ "transformer.h.2.ln_1.bias": "model-00001-of-00005.safetensors",
132
+ "transformer.h.2.ln_1.weight": "model-00001-of-00005.safetensors",
133
+ "transformer.h.2.ln_2.bias": "model-00001-of-00005.safetensors",
134
+ "transformer.h.2.ln_2.weight": "model-00001-of-00005.safetensors",
135
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
136
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
137
+ "transformer.h.20.attn.bias": "model-00003-of-00005.safetensors",
138
+ "transformer.h.20.attn.c_attn.weight": "model-00003-of-00005.safetensors",
139
+ "transformer.h.20.attn.c_proj.weight": "model-00003-of-00005.safetensors",
140
+ "transformer.h.20.attn.masked_bias": "model-00003-of-00005.safetensors",
141
+ "transformer.h.20.ln_1.bias": "model-00003-of-00005.safetensors",
142
+ "transformer.h.20.ln_1.weight": "model-00003-of-00005.safetensors",
143
+ "transformer.h.20.ln_2.bias": "model-00003-of-00005.safetensors",
144
+ "transformer.h.20.ln_2.weight": "model-00003-of-00005.safetensors",
145
+ "transformer.h.20.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
146
+ "transformer.h.20.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
147
+ "transformer.h.21.attn.bias": "model-00003-of-00005.safetensors",
148
+ "transformer.h.21.attn.c_attn.weight": "model-00003-of-00005.safetensors",
149
+ "transformer.h.21.attn.c_proj.weight": "model-00003-of-00005.safetensors",
150
+ "transformer.h.21.attn.masked_bias": "model-00003-of-00005.safetensors",
151
+ "transformer.h.21.ln_1.bias": "model-00003-of-00005.safetensors",
152
+ "transformer.h.21.ln_1.weight": "model-00003-of-00005.safetensors",
153
+ "transformer.h.21.ln_2.bias": "model-00003-of-00005.safetensors",
154
+ "transformer.h.21.ln_2.weight": "model-00003-of-00005.safetensors",
155
+ "transformer.h.21.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
156
+ "transformer.h.21.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
157
+ "transformer.h.22.attn.bias": "model-00003-of-00005.safetensors",
158
+ "transformer.h.22.attn.c_attn.weight": "model-00003-of-00005.safetensors",
159
+ "transformer.h.22.attn.c_proj.weight": "model-00003-of-00005.safetensors",
160
+ "transformer.h.22.attn.masked_bias": "model-00003-of-00005.safetensors",
161
+ "transformer.h.22.ln_1.bias": "model-00003-of-00005.safetensors",
162
+ "transformer.h.22.ln_1.weight": "model-00003-of-00005.safetensors",
163
+ "transformer.h.22.ln_2.bias": "model-00003-of-00005.safetensors",
164
+ "transformer.h.22.ln_2.weight": "model-00003-of-00005.safetensors",
165
+ "transformer.h.22.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
166
+ "transformer.h.22.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
167
+ "transformer.h.23.attn.bias": "model-00003-of-00005.safetensors",
168
+ "transformer.h.23.attn.c_attn.weight": "model-00003-of-00005.safetensors",
169
+ "transformer.h.23.attn.c_proj.weight": "model-00003-of-00005.safetensors",
170
+ "transformer.h.23.attn.masked_bias": "model-00003-of-00005.safetensors",
171
+ "transformer.h.23.ln_1.bias": "model-00003-of-00005.safetensors",
172
+ "transformer.h.23.ln_1.weight": "model-00003-of-00005.safetensors",
173
+ "transformer.h.23.ln_2.bias": "model-00003-of-00005.safetensors",
174
+ "transformer.h.23.ln_2.weight": "model-00003-of-00005.safetensors",
175
+ "transformer.h.23.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
176
+ "transformer.h.23.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
177
+ "transformer.h.24.attn.bias": "model-00004-of-00005.safetensors",
178
+ "transformer.h.24.attn.c_attn.weight": "model-00004-of-00005.safetensors",
179
+ "transformer.h.24.attn.c_proj.weight": "model-00004-of-00005.safetensors",
180
+ "transformer.h.24.attn.masked_bias": "model-00004-of-00005.safetensors",
181
+ "transformer.h.24.ln_1.bias": "model-00004-of-00005.safetensors",
182
+ "transformer.h.24.ln_1.weight": "model-00004-of-00005.safetensors",
183
+ "transformer.h.24.ln_2.bias": "model-00004-of-00005.safetensors",
184
+ "transformer.h.24.ln_2.weight": "model-00004-of-00005.safetensors",
185
+ "transformer.h.24.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
186
+ "transformer.h.24.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
187
+ "transformer.h.25.attn.bias": "model-00004-of-00005.safetensors",
188
+ "transformer.h.25.attn.c_attn.weight": "model-00004-of-00005.safetensors",
189
+ "transformer.h.25.attn.c_proj.weight": "model-00004-of-00005.safetensors",
190
+ "transformer.h.25.attn.masked_bias": "model-00004-of-00005.safetensors",
191
+ "transformer.h.25.ln_1.bias": "model-00004-of-00005.safetensors",
192
+ "transformer.h.25.ln_1.weight": "model-00004-of-00005.safetensors",
193
+ "transformer.h.25.ln_2.bias": "model-00004-of-00005.safetensors",
194
+ "transformer.h.25.ln_2.weight": "model-00004-of-00005.safetensors",
195
+ "transformer.h.25.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
196
+ "transformer.h.25.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
197
+ "transformer.h.26.attn.bias": "model-00004-of-00005.safetensors",
198
+ "transformer.h.26.attn.c_attn.weight": "model-00004-of-00005.safetensors",
199
+ "transformer.h.26.attn.c_proj.weight": "model-00004-of-00005.safetensors",
200
+ "transformer.h.26.attn.masked_bias": "model-00004-of-00005.safetensors",
201
+ "transformer.h.26.ln_1.bias": "model-00004-of-00005.safetensors",
202
+ "transformer.h.26.ln_1.weight": "model-00004-of-00005.safetensors",
203
+ "transformer.h.26.ln_2.bias": "model-00004-of-00005.safetensors",
204
+ "transformer.h.26.ln_2.weight": "model-00004-of-00005.safetensors",
205
+ "transformer.h.26.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
206
+ "transformer.h.26.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
207
+ "transformer.h.27.attn.bias": "model-00004-of-00005.safetensors",
208
+ "transformer.h.27.attn.c_attn.weight": "model-00004-of-00005.safetensors",
209
+ "transformer.h.27.attn.c_proj.weight": "model-00004-of-00005.safetensors",
210
+ "transformer.h.27.attn.masked_bias": "model-00004-of-00005.safetensors",
211
+ "transformer.h.27.ln_1.bias": "model-00004-of-00005.safetensors",
212
+ "transformer.h.27.ln_1.weight": "model-00004-of-00005.safetensors",
213
+ "transformer.h.27.ln_2.bias": "model-00004-of-00005.safetensors",
214
+ "transformer.h.27.ln_2.weight": "model-00004-of-00005.safetensors",
215
+ "transformer.h.27.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
216
+ "transformer.h.27.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
217
+ "transformer.h.28.attn.bias": "model-00004-of-00005.safetensors",
218
+ "transformer.h.28.attn.c_attn.weight": "model-00004-of-00005.safetensors",
219
+ "transformer.h.28.attn.c_proj.weight": "model-00004-of-00005.safetensors",
220
+ "transformer.h.28.attn.masked_bias": "model-00004-of-00005.safetensors",
221
+ "transformer.h.28.ln_1.bias": "model-00004-of-00005.safetensors",
222
+ "transformer.h.28.ln_1.weight": "model-00004-of-00005.safetensors",
223
+ "transformer.h.28.ln_2.bias": "model-00004-of-00005.safetensors",
224
+ "transformer.h.28.ln_2.weight": "model-00004-of-00005.safetensors",
225
+ "transformer.h.28.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
226
+ "transformer.h.28.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
227
+ "transformer.h.29.attn.bias": "model-00004-of-00005.safetensors",
228
+ "transformer.h.29.attn.c_attn.weight": "model-00004-of-00005.safetensors",
229
+ "transformer.h.29.attn.c_proj.weight": "model-00004-of-00005.safetensors",
230
+ "transformer.h.29.attn.masked_bias": "model-00004-of-00005.safetensors",
231
+ "transformer.h.29.ln_1.bias": "model-00004-of-00005.safetensors",
232
+ "transformer.h.29.ln_1.weight": "model-00004-of-00005.safetensors",
233
+ "transformer.h.29.ln_2.bias": "model-00004-of-00005.safetensors",
234
+ "transformer.h.29.ln_2.weight": "model-00004-of-00005.safetensors",
235
+ "transformer.h.29.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
236
+ "transformer.h.29.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
237
+ "transformer.h.3.attn.bias": "model-00001-of-00005.safetensors",
238
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00005.safetensors",
239
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00005.safetensors",
240
+ "transformer.h.3.attn.masked_bias": "model-00001-of-00005.safetensors",
241
+ "transformer.h.3.ln_1.bias": "model-00001-of-00005.safetensors",
242
+ "transformer.h.3.ln_1.weight": "model-00001-of-00005.safetensors",
243
+ "transformer.h.3.ln_2.bias": "model-00001-of-00005.safetensors",
244
+ "transformer.h.3.ln_2.weight": "model-00001-of-00005.safetensors",
245
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
246
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
247
+ "transformer.h.30.attn.bias": "model-00004-of-00005.safetensors",
248
+ "transformer.h.30.attn.c_attn.weight": "model-00004-of-00005.safetensors",
249
+ "transformer.h.30.attn.c_proj.weight": "model-00004-of-00005.safetensors",
250
+ "transformer.h.30.attn.masked_bias": "model-00004-of-00005.safetensors",
251
+ "transformer.h.30.ln_1.bias": "model-00004-of-00005.safetensors",
252
+ "transformer.h.30.ln_1.weight": "model-00004-of-00005.safetensors",
253
+ "transformer.h.30.ln_2.bias": "model-00004-of-00005.safetensors",
254
+ "transformer.h.30.ln_2.weight": "model-00004-of-00005.safetensors",
255
+ "transformer.h.30.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
256
+ "transformer.h.30.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
257
+ "transformer.h.31.attn.bias": "model-00004-of-00005.safetensors",
258
+ "transformer.h.31.attn.c_attn.weight": "model-00004-of-00005.safetensors",
259
+ "transformer.h.31.attn.c_proj.weight": "model-00004-of-00005.safetensors",
260
+ "transformer.h.31.attn.masked_bias": "model-00004-of-00005.safetensors",
261
+ "transformer.h.31.ln_1.bias": "model-00004-of-00005.safetensors",
262
+ "transformer.h.31.ln_1.weight": "model-00004-of-00005.safetensors",
263
+ "transformer.h.31.ln_2.bias": "model-00004-of-00005.safetensors",
264
+ "transformer.h.31.ln_2.weight": "model-00004-of-00005.safetensors",
265
+ "transformer.h.31.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
266
+ "transformer.h.31.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
267
+ "transformer.h.4.attn.bias": "model-00001-of-00005.safetensors",
268
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00005.safetensors",
269
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00005.safetensors",
270
+ "transformer.h.4.attn.masked_bias": "model-00001-of-00005.safetensors",
271
+ "transformer.h.4.ln_1.bias": "model-00001-of-00005.safetensors",
272
+ "transformer.h.4.ln_1.weight": "model-00001-of-00005.safetensors",
273
+ "transformer.h.4.ln_2.bias": "model-00001-of-00005.safetensors",
274
+ "transformer.h.4.ln_2.weight": "model-00001-of-00005.safetensors",
275
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
276
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
277
+ "transformer.h.5.attn.bias": "model-00001-of-00005.safetensors",
278
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00005.safetensors",
279
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00005.safetensors",
280
+ "transformer.h.5.attn.masked_bias": "model-00001-of-00005.safetensors",
281
+ "transformer.h.5.ln_1.bias": "model-00001-of-00005.safetensors",
282
+ "transformer.h.5.ln_1.weight": "model-00001-of-00005.safetensors",
283
+ "transformer.h.5.ln_2.bias": "model-00001-of-00005.safetensors",
284
+ "transformer.h.5.ln_2.weight": "model-00001-of-00005.safetensors",
285
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
286
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
287
+ "transformer.h.6.attn.bias": "model-00001-of-00005.safetensors",
288
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00005.safetensors",
289
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00005.safetensors",
290
+ "transformer.h.6.attn.masked_bias": "model-00001-of-00005.safetensors",
291
+ "transformer.h.6.ln_1.bias": "model-00001-of-00005.safetensors",
292
+ "transformer.h.6.ln_1.weight": "model-00001-of-00005.safetensors",
293
+ "transformer.h.6.ln_2.bias": "model-00001-of-00005.safetensors",
294
+ "transformer.h.6.ln_2.weight": "model-00001-of-00005.safetensors",
295
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
296
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
297
+ "transformer.h.7.attn.bias": "model-00001-of-00005.safetensors",
298
+ "transformer.h.7.attn.c_attn.weight": "model-00002-of-00005.safetensors",
299
+ "transformer.h.7.attn.c_proj.weight": "model-00002-of-00005.safetensors",
300
+ "transformer.h.7.attn.masked_bias": "model-00001-of-00005.safetensors",
301
+ "transformer.h.7.ln_1.bias": "model-00001-of-00005.safetensors",
302
+ "transformer.h.7.ln_1.weight": "model-00001-of-00005.safetensors",
303
+ "transformer.h.7.ln_2.bias": "model-00002-of-00005.safetensors",
304
+ "transformer.h.7.ln_2.weight": "model-00002-of-00005.safetensors",
305
+ "transformer.h.7.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
306
+ "transformer.h.7.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
307
+ "transformer.h.8.attn.bias": "model-00002-of-00005.safetensors",
308
+ "transformer.h.8.attn.c_attn.weight": "model-00002-of-00005.safetensors",
309
+ "transformer.h.8.attn.c_proj.weight": "model-00002-of-00005.safetensors",
310
+ "transformer.h.8.attn.masked_bias": "model-00002-of-00005.safetensors",
311
+ "transformer.h.8.ln_1.bias": "model-00002-of-00005.safetensors",
312
+ "transformer.h.8.ln_1.weight": "model-00002-of-00005.safetensors",
313
+ "transformer.h.8.ln_2.bias": "model-00002-of-00005.safetensors",
314
+ "transformer.h.8.ln_2.weight": "model-00002-of-00005.safetensors",
315
+ "transformer.h.8.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
316
+ "transformer.h.8.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
317
+ "transformer.h.9.attn.bias": "model-00002-of-00005.safetensors",
318
+ "transformer.h.9.attn.c_attn.weight": "model-00002-of-00005.safetensors",
319
+ "transformer.h.9.attn.c_proj.weight": "model-00002-of-00005.safetensors",
320
+ "transformer.h.9.attn.masked_bias": "model-00002-of-00005.safetensors",
321
+ "transformer.h.9.ln_1.bias": "model-00002-of-00005.safetensors",
322
+ "transformer.h.9.ln_1.weight": "model-00002-of-00005.safetensors",
323
+ "transformer.h.9.ln_2.bias": "model-00002-of-00005.safetensors",
324
+ "transformer.h.9.ln_2.weight": "model-00002-of-00005.safetensors",
325
+ "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
326
+ "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
327
+ "transformer.ln_f.bias": "model-00004-of-00005.safetensors",
328
+ "transformer.ln_f.weight": "model-00004-of-00005.safetensors",
329
+ "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00005.safetensors",
330
+ "transformer.wte.weight": "model-00001-of-00005.safetensors"
331
+ }
332
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "auto_map": {
38
+ "AutoTokenizer": [
39
+ "KT-AI/midm-bitext-S-7B-inst-v1--midm_bitext_tokenization.Midm_bitext_Tokenizer",
40
+ null
41
+ ]
42
+ },
43
+ "clean_up_tokenization_spaces": true,
44
+ "eos_token": "</s>",
45
+ "extra_ids": 0,
46
+ "model_max_length": 1000000000000000019884624838656,
47
+ "pad_token": "<pad>",
48
+ "sp_model_kwargs": {},
49
+ "tokenizer_class": "Midm_bitext_Tokenizer",
50
+ "tokenizer_file": null,
51
+ "unk_token": "<unk>"
52
+ }