Hugging Face's logo

ayjays132
/
PHILLNET-1

Text Generation
Transformers
PyTorch
Safetensors
English
gpt2
conversational
dynamic
adaptive
text-generation-inference
Model card Files
xet
Community
1
ayjays132 commited on
Commit
af742f5
·
verified ·
1 Parent(s): 8fefcae

Upload 17 files

Browse files
Files changed (17) hide show
  1. added_tokens.json +25 -0
  2. config.json +17 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. optimizer.pt +3 -0
  6. pytorch_model-00001-of-00002.bin +3 -0
  7. pytorch_model-00002-of-00002.bin +3 -0
  8. pytorch_model.bin.index.json +0 -0
  9. rng_state.pth +3 -0
  10. scaler.pt +3 -0
  11. scheduler.pt +3 -0
  12. special_tokens_map.json +55 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +237 -0
  15. trainer_state.json +32 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</auditory_input>": 50271,
3
+ "</auditory_output>": 50277,
4
+ "</evaluate>": 50267,
5
+ "</internal_thinking>": 50261,
6
+ "</plan>": 50265,
7
+ "</reasoning>": 50263,
8
+ "</s>": 50259,
9
+ "</tactile_input>": 50273,
10
+ "</tactile_output>": 50279,
11
+ "</visual_input>": 50269,
12
+ "</visual_output>": 50275,
13
+ "<auditory_input>": 50270,
14
+ "<auditory_output>": 50276,
15
+ "<evaluate>": 50266,
16
+ "<internal_thinking>": 50260,
17
+ "<pad>": 50257,
18
+ "<plan>": 50264,
19
+ "<reasoning>": 50262,
20
+ "<s>": 50258,
21
+ "<tactile_input>": 50272,
22
+ "<tactile_output>": 50278,
23
+ "<visual_input>": 50268,
24
+ "<visual_output>": 50274
25
+ }
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adaptation_rate": 0.01,
3
+ "architectures": [
4
+ "DynamicNeuralNetwork"
5
+ ],
6
+ "bos_token_id": 50256,
7
+ "eos_token_id": 50256,
8
+ "max_neurons": 8192,
9
+ "moe_load_balancing_weight": 0.01,
10
+ "moe_router_z_loss_weight": 0.001,
11
+ "moe_top_k": 4,
12
+ "num_moe_experts": 16,
13
+ "pad_token_id": 50256,
14
+ "reward_loss_weight": 0.1,
15
+ "torch_dtype": "float32",
16
+ "vocab_size": 50280
17
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.49.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab620ccd1457defb275e2190c1b6b7946ad1d0f4bec20ad8400756b4e6ddfd19
3
+ size 51624
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badfb4eb7df079642237e9f944cd0040da96808ebf1355095d146cff7087be7a
3
+ size 5004049233
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a171d6fe6d1d840e0fb7a23c03f0361b98d6fd23fb79c077c18efaf125037a40
3
+ size 769579254
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9851ad32c4e0ad0da405a48c3ec889cc14dd3dc2c68a992facd9724babccbafe
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd88c1400734381e4f63d3ace0ea9a85534c65976e4e34bd6f4e74b7cb7c880b
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24712a3aafb7674c0670bb054afa3785b078b5ba01826f54d21063188b9ec55c
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "<s>",
5
+ "</s>",
6
+ "<internal_thinking>",
7
+ "</internal_thinking>",
8
+ "<reasoning>",
9
+ "</reasoning>",
10
+ "<plan>",
11
+ "</plan>",
12
+ "<evaluate>",
13
+ "</evaluate>",
14
+ "<visual_input>",
15
+ "</visual_input>",
16
+ "<auditory_input>",
17
+ "</auditory_input>",
18
+ "<tactile_input>",
19
+ "</tactile_input>",
20
+ "<visual_output>",
21
+ "</visual_output>",
22
+ "<auditory_output>",
23
+ "</auditory_output>",
24
+ "<tactile_output>",
25
+ "</tactile_output>"
26
+ ],
27
+ "bos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "eos_token": {
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "pad_token": {
42
+ "content": "<|endoftext|>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<|endoftext|>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50257": {
14
+ "content": "<pad>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "<s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50259": {
30
+ "content": "</s>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<internal_thinking>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "</internal_thinking>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<reasoning>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "</reasoning>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50264": {
70
+ "content": "<plan>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50265": {
78
+ "content": "</plan>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50266": {
86
+ "content": "<evaluate>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50267": {
94
+ "content": "</evaluate>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "50268": {
102
+ "content": "<visual_input>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "50269": {
110
+ "content": "</visual_input>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "50270": {
118
+ "content": "<auditory_input>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "50271": {
126
+ "content": "</auditory_input>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "50272": {
134
+ "content": "<tactile_input>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "50273": {
142
+ "content": "</tactile_input>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "50274": {
150
+ "content": "<visual_output>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "50275": {
158
+ "content": "</visual_output>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "50276": {
166
+ "content": "<auditory_output>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "50277": {
174
+ "content": "</auditory_output>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "50278": {
182
+ "content": "<tactile_output>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "50279": {
190
+ "content": "</tactile_output>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ }
197
+ },
198
+ "additional_special_tokens": [
199
+ "<pad>",
200
+ "<s>",
201
+ "</s>",
202
+ "<internal_thinking>",
203
+ "</internal_thinking>",
204
+ "<reasoning>",
205
+ "</reasoning>",
206
+ "<plan>",
207
+ "</plan>",
208
+ "<evaluate>",
209
+ "</evaluate>",
210
+ "<visual_input>",
211
+ "</visual_input>",
212
+ "<auditory_input>",
213
+ "</auditory_input>",
214
+ "<tactile_input>",
215
+ "</tactile_input>",
216
+ "<visual_output>",
217
+ "</visual_output>",
218
+ "<auditory_output>",
219
+ "</auditory_output>",
220
+ "<tactile_output>",
221
+ "</tactile_output>"
222
+ ],
223
+ "bos_token": "<|endoftext|>",
224
+ "clean_up_tokenization_spaces": false,
225
+ "eos_token": "<|endoftext|>",
226
+ "errors": "replace",
227
+ "extra_special_tokens": {},
228
+ "max_length": 1024,
229
+ "model_max_length": 1024,
230
+ "pad_token": "<|endoftext|>",
231
+ "padding_side": "left",
232
+ "stride": 0,
233
+ "tokenizer_class": "GPT2Tokenizer",
234
+ "truncation_side": "right",
235
+ "truncation_strategy": "longest_first",
236
+ "unk_token": "<|endoftext|>"
237
+ }
trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.016129032258064516,
5
+ "eval_steps": 1,
6
+ "global_step": 1,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 100,
12
+ "max_steps": 186,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 1,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": false
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 93822155378688.0,
29
+ "train_batch_size": 22,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668b56f0110a8fec2ddec0e6330a327029f7602abb7dd83c5f4322fc84e2308f
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff