Pclanglais commited on
Commit
1e06991
·
verified ·
1 Parent(s): d1b2f8e

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2560,
13
+ "max_position_embeddings": 2048,
14
+ "mlp_bias": false,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 26,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.44.2",
26
+ "use_cache": true,
27
+ "vocab_size": 65536
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5726f7dd01eee15c2bb527606aebc24ec0aaabc5b9753425fb38db9c61d747b
3
+ size 706875632
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|text|>",
4
+ "<|text_summary|>",
5
+ "<|text_narrative|>",
6
+ "<|text_enonciation|>",
7
+ "<|text_tone|>",
8
+ "<|text_genre|>",
9
+ "<|text_intertext|>",
10
+ "<|text_speech|>",
11
+ "<|text_form|>",
12
+ "<|text_protagonist|>",
13
+ "<|text_cited_person|>",
14
+ "<|text_time|>",
15
+ "<|text_diegetic_time|>",
16
+ "<|text_place|>",
17
+ "<|text_language|>",
18
+ "<|text_previous|>"
19
+ ]
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|end_of_text|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "65536": {
36
+ "content": "<|text|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "65537": {
44
+ "content": "<|text_summary|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "65538": {
52
+ "content": "<|text_narrative|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "65539": {
60
+ "content": "<|text_enonciation|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "65540": {
68
+ "content": "<|text_tone|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "65541": {
76
+ "content": "<|text_genre|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "65542": {
84
+ "content": "<|text_intertext|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "65543": {
92
+ "content": "<|text_speech|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "65544": {
100
+ "content": "<|text_form|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "65545": {
108
+ "content": "<|text_protagonist|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "65546": {
116
+ "content": "<|text_cited_person|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "65547": {
124
+ "content": "<|text_time|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "65548": {
132
+ "content": "<|text_diegetic_time|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "65549": {
140
+ "content": "<|text_place|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "65550": {
148
+ "content": "<|text_language|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "65551": {
156
+ "content": "<|text_previous|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ }
163
+ },
164
+ "additional_special_tokens": [
165
+ "<|text|>",
166
+ "<|text_summary|>",
167
+ "<|text_narrative|>",
168
+ "<|text_enonciation|>",
169
+ "<|text_tone|>",
170
+ "<|text_genre|>",
171
+ "<|text_intertext|>",
172
+ "<|text_speech|>",
173
+ "<|text_form|>",
174
+ "<|text_protagonist|>",
175
+ "<|text_cited_person|>",
176
+ "<|text_time|>",
177
+ "<|text_diegetic_time|>",
178
+ "<|text_place|>",
179
+ "<|text_language|>",
180
+ "<|text_previous|>"
181
+ ],
182
+ "clean_up_tokenization_spaces": true,
183
+ "model_max_length": 1000000000000000019884624838656,
184
+ "tokenizer_class": "PreTrainedTokenizerFast"
185
+ }