Hugging Face's logo

amirabdullah19852020
/
test

Text Generation
Transformers
Safetensors
gemma
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
amirabdullah19852020 commited on
Commit
e83710b
•
1 Parent(s): 4ac45c6

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +45 -20
  2. merges.txt +0 -0
  3. model.safetensors +2 -2
  4. special_tokens_map.json +3 -3
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +6 -196
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,30 +1,55 @@
1
  {
2
- "_name_or_path": "EleutherAI/pythia-410m",
 
3
  "architectures": [
4
- "GPTNeoXForCausalLM"
5
  ],
6
- "attention_bias": true,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "classifier_dropout": 0.1,
10
- "eos_token_id": 0,
11
- "hidden_act": "gelu",
12
- "hidden_dropout": 0.0,
13
- "hidden_size": 1024,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 4096,
16
- "layer_norm_eps": 1e-05,
17
  "max_position_embeddings": 2048,
18
- "model_type": "gpt_neox",
19
- "num_attention_heads": 16,
20
- "num_hidden_layers": 24,
21
- "rope_scaling": null,
22
- "rotary_emb_base": 10000,
23
- "rotary_pct": 0.25,
24
- "tie_word_embeddings": false,
 
 
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.38.2",
27
  "use_cache": true,
28
- "use_parallel_residual": true,
29
- "vocab_size": 50304
30
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125m",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPTNeoForCausalLM"
6
  ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
  "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
  "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
  "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
  "torch_dtype": "bfloat16",
51
  "transformers_version": "4.38.2",
52
  "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17032eae514624f7bd15cce60b693056e65282609555b95aafecddf3c40aa90e
3
- size 810702192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3943eac45061f4462426c18512260e47be3a7e0081c8614b905eaa9df3169b6
3
+ size 250414224
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
- "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
20
- "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
+ "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
20
+ "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,212 +1,22 @@
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "0": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<|padding|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "50254": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50255": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
  "50256": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50257": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50258": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50259": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50260": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50261": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50262": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50263": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50264": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50265": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50266": {
117
- "content": " ",
118
- "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50267": {
125
- "content": " ",
126
- "lstrip": false,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "50268": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50269": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50270": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50271": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50272": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50273": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50274": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50275": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50276": {
197
- "content": " ",
198
  "lstrip": false,
199
  "normalized": true,
200
  "rstrip": false,
201
  "single_word": false,
202
- "special": false
203
  }
204
  },
205
  "bos_token": "<|endoftext|>",
206
  "clean_up_tokenization_spaces": true,
207
  "eos_token": "<|endoftext|>",
208
- "model_max_length": 1000000000000000019884624838656,
 
209
  "pad_token": "<|endoftext|>",
210
- "tokenizer_class": "GPTNeoXTokenizer",
211
  "unk_token": "<|endoftext|>"
212
  }
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "50256": {
6
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
+ "special": true
12
  }
13
  },
14
  "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
  "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
  "unk_token": "<|endoftext|>"
22
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a432f4f3c5e8de4bfd15d9ef766992e36eef8b51f7bbd2bf29a249637b725c6
3
  size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cde70c0b096fbe91344a403e483244871c8d44178287b6992efc53de8ad8ca
3
  size 4411
vocab.json ADDED
The diff for this file is too large to render. See raw diff