Hugging Face's logo

yzhuang
/
phi-1_5_fictional

Text Generation
Transformers
Safetensors
llama
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
yzhuang commited on
Commit
49700a5
•
1 Parent(s): 419f00e

Training in progress, step 2500

Browse files
Files changed (7) hide show
  1. config.json +24 -21
  2. model.safetensors +2 -2
  3. special_tokens_map.json +7 -13
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +308 -14
  6. training_args.bin +1 -1
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,31 +1,34 @@
1
  {
2
- "_name_or_path": "facebook/opt-350m",
3
- "_remove_final_layer_norm": false,
4
- "activation_dropout": 0.0,
5
- "activation_function": "relu",
6
  "architectures": [
7
- "OPTForCausalLM"
8
  ],
9
  "attention_dropout": 0.0,
10
- "bos_token_id": 2,
11
- "do_layer_norm_before": false,
12
- "dropout": 0.1,
13
- "enable_bias": true,
14
- "eos_token_id": 2,
15
- "ffn_dim": 4096,
16
- "hidden_size": 1024,
17
- "init_std": 0.02,
18
- "layer_norm_elementwise_affine": true,
19
- "layerdrop": 0.0,
 
 
20
  "max_position_embeddings": 2048,
21
- "model_type": "opt",
22
- "num_attention_heads": 16,
23
  "num_hidden_layers": 24,
24
- "pad_token_id": 1,
25
- "prefix": "</s>",
 
 
 
 
 
26
  "torch_dtype": "float16",
27
  "transformers_version": "4.36.2",
28
  "use_cache": true,
29
- "vocab_size": 50272,
30
- "word_embed_proj_dim": 512
31
  }
 
1
  {
2
+ "_name_or_path": "microsoft/phi-1_5",
 
 
 
3
  "architectures": [
4
+ "PhiForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": null,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": null,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "layer_norm_eps": 1e-05,
19
  "max_position_embeddings": 2048,
20
+ "model_type": "phi",
21
+ "num_attention_heads": 32,
22
  "num_hidden_layers": 24,
23
+ "num_key_value_heads": 32,
24
+ "partial_rotary_factor": 0.5,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.0,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
  "torch_dtype": "float16",
31
  "transformers_version": "4.36.2",
32
  "use_cache": true,
33
+ "vocab_size": 51200
 
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c314039e8cf6c559b7d0aa4a35a35c605e6d18b21ac445964ec5b234c46a00e
3
- size 662437776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bcba9d57ea4e00a3a553084f4d8ea57bb65206ea7caab2710623a7e2e67e0a
3
+ size 2836578696
special_tokens_map.json CHANGED
@@ -1,29 +1,23 @@
1
  {
2
  "bos_token": {
3
- "content": "</s>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<pad>",
18
- "lstrip": false,
19
- "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  },
 
23
  "unk_token": {
24
- "content": "</s>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
1
  {
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
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
+ "normalized": false,
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
@@ -1,30 +1,324 @@
1
  {
2
- "add_bos_token": true,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "1": {
6
- "content": "<pad>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "2": {
14
- "content": "</s>",
15
  "lstrip": false,
16
  "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  }
21
  },
22
- "bos_token": "</s>",
23
  "clean_up_tokenization_spaces": true,
24
- "eos_token": "</s>",
25
- "errors": "replace",
26
- "model_max_length": 1000000000000000019884624838656,
27
- "pad_token": "<pad>",
28
- "tokenizer_class": "GPT2Tokenizer",
29
- "unk_token": "</s>"
30
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "50257": {
13
+ "content": " ",
14
  "lstrip": false,
15
  "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
  }
316
  },
317
+ "bos_token": "<|endoftext|>",
318
  "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
 
324
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:223965d396f643b279255b921cb5c585821f1be9801a67ac3201942f3e78eded
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb6d3afd04dfed8509f1ef61a582549c76417657999a12b99466e317af15a9d
3
  size 4664
vocab.json CHANGED
The diff for this file is too large to render. See raw diff