Hugging Face's logo

KBlueLeaf
/
TIPO-500M

Text Generation
Transformers
Safetensors
GGUF
English
llama
text-generation-inference
Model card Files
xet
 Community
2
KBlueLeaf commited on
Commit
edf23a3
·
verified ·
1 Parent(s): 9d2d8fd

Upload 8 files

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. TIPO-500M_epoch5-F16.gguf +3 -0
  3. added_tokens.json +15 -0
  4. config.json +30 -0
  5. generation_config.json +8 -0
  6. model.safetensors +3 -0
  7. special_tokens_map.json +45 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +162 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ TIPO-500M_epoch5-F16.gguf filter=lfs diff=lfs merge=lfs -text
TIPO-500M_epoch5-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c711f55fa47e59523e073936b3a81876403d0f227b345f15cf7aabe31dd0614
3
+ size 1016819840
added_tokens.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|empty|>": 32000,
3
+ "<|gen_meta|>": 32012,
4
+ "<|long_to_tag|>": 32006,
5
+ "<|long|>": 32003,
6
+ "<|short_to_long_to_tag|>": 32011,
7
+ "<|short_to_long|>": 32008,
8
+ "<|short_to_tag_to_long|>": 32010,
9
+ "<|short_to_tag|>": 32007,
10
+ "<|short|>": 32002,
11
+ "<|tag_to_long|>": 32005,
12
+ "<|tag_to_short_to_long|>": 32009,
13
+ "<|very_long|>": 32004,
14
+ "<|very_short|>": 32001
15
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./config/arch/NanoLLaMA-500m.json",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1280,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3840,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 20,
19
+ "num_key_value_heads": 20,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.44.2",
28
+ "use_cache": false,
29
+ "vocab_size": 32013
30
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.44.2",
7
+ "use_cache": false
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa6063be163426a0a15a0b183631855f97df30169703ae05349c8c63a587c1f
3
+ size 2031979904
special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|empty|>",
4
+ "<|very_short|>",
5
+ "<|short|>",
6
+ "<|long|>",
7
+ "<|very_long|>",
8
+ "<|tag_to_long|>",
9
+ "<|long_to_tag|>",
10
+ "<|short_to_tag|>",
11
+ "<|short_to_long|>",
12
+ "<|tag_to_short_to_long|>",
13
+ "<|short_to_tag_to_long|>",
14
+ "<|short_to_long_to_tag|>",
15
+ "<|gen_meta|>"
16
+ ],
17
+ "bos_token": {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "eos_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "unk_token": {
39
+ "content": "<unk>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|empty|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|very_short|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|short|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|long|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|very_long|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|tag_to_long|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|long_to_tag|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|short_to_tag|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|short_to_long|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|tag_to_short_to_long|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|short_to_tag_to_long|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|short_to_long_to_tag|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|gen_meta|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ }
134
+ },
135
+ "additional_special_tokens": [
136
+ "<|empty|>",
137
+ "<|very_short|>",
138
+ "<|short|>",
139
+ "<|long|>",
140
+ "<|very_long|>",
141
+ "<|tag_to_long|>",
142
+ "<|long_to_tag|>",
143
+ "<|short_to_tag|>",
144
+ "<|short_to_long|>",
145
+ "<|tag_to_short_to_long|>",
146
+ "<|short_to_tag_to_long|>",
147
+ "<|short_to_long_to_tag|>",
148
+ "<|gen_meta|>"
149
+ ],
150
+ "bos_token": "<s>",
151
+ "clean_up_tokenization_spaces": false,
152
+ "eos_token": "</s>",
153
+ "legacy": false,
154
+ "model_max_length": 1000000000000000019884624838656,
155
+ "pad_token": "</s>",
156
+ "padding_side": "right",
157
+ "sp_model_kwargs": {},
158
+ "spaces_between_special_tokens": false,
159
+ "tokenizer_class": "LlamaTokenizer",
160
+ "unk_token": "<unk>",
161
+ "use_default_system_prompt": false
162
+ }