PetarStika commited on
Commit
c49b53b
·
verified ·
1 Parent(s): e27aebf

Upload folder using huggingface_hub

Browse files
README.md ADDED
File without changes
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": 8.0,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 1,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.45.2",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.45.2"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17329fe1b6c90d97d80f5fd0ea0bde7d969b3ab4d597b126f4a4029285811e35
3
+ size 4707070632
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24481fcc1d0dbf8b615d448434da5553c36edc88abd5687e244ab957271c8e16
3
+ size 412090496
model.safetensors.index.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5119148032
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
120
+ }
121
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|padding|>"
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ }
230
+ },
231
+ "bos_token": null,
232
+ "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|endoftext|>",
234
+ "model_max_length": 1000000000000000019884624838656,
235
+ "pad_token": "<|padding|>",
236
+ "tokenizer_class": "GPTNeoXTokenizer",
237
+ "unk_token": null
238
+ }