Hugging Face's logo

SykoSLM
/
SykoLLM-V2.9-Thinking-Beta

Safetensors
Turkish
gpt2
Model card Files
xet
 Community
burak commited on
Commit
fb7bc8e
·
verified ·
1 Parent(s): d99ea5c

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. added_tokens.json +9 -0
  2. config.json +33 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +34 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +90 -0
  9. trainer_state.json +174 -0
  10. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</thinking>": 50261,
3
+ "<bos>": 50257,
4
+ "<eos>": 50258,
5
+ "<pad>": 50259,
6
+ "<thinking>": 50260,
7
+ "<|pad|>": 50263,
8
+ "<|startoftext|>": 50262
9
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50257,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50258,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 22,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50259,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.57.3",
31
+ "use_cache": true,
32
+ "vocab_size": 50264
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "eos_token_id": 50258,
5
+ "pad_token_id": 50259,
6
+ "transformers_version": "4.57.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2721362a2d9cc59c9cab672a140c3a103abb10d8f369312b87ba352ba7fdff
3
+ size 1318579224
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<thinking>",
4
+ "</thinking>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<eos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<bos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "<eos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50259": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<thinking>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "</thinking>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<|startoftext|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "<|pad|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ }
69
+ },
70
+ "additional_special_tokens": [
71
+ "<thinking>",
72
+ "</thinking>"
73
+ ],
74
+ "bos_token": "<bos>",
75
+ "clean_up_tokenization_spaces": false,
76
+ "eos_token": "<eos>",
77
+ "errors": "replace",
78
+ "extra_special_tokens": {},
79
+ "max_length": 256,
80
+ "model_max_length": 2048,
81
+ "pad_to_multiple_of": null,
82
+ "pad_token": "<eos>",
83
+ "pad_token_type_id": 0,
84
+ "padding_side": "right",
85
+ "stride": 0,
86
+ "tokenizer_class": "GPT2Tokenizer",
87
+ "truncation_side": "right",
88
+ "truncation_strategy": "longest_first",
89
+ "unk_token": "<|endoftext|>"
90
+ }
trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.32,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.016,
14
+ "grad_norm": 0.987720251083374,
15
+ "learning_rate": 3.997524171965045e-05,
16
+ "loss": 4.506,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.032,
21
+ "grad_norm": 1.1270077228546143,
22
+ "learning_rate": 3.990002677172515e-05,
23
+ "loss": 4.1703,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.048,
28
+ "grad_norm": 0.9228858351707458,
29
+ "learning_rate": 3.9774542629091646e-05,
30
+ "loss": 3.9996,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.064,
35
+ "grad_norm": 0.9696429371833801,
36
+ "learning_rate": 3.9599106275584746e-05,
37
+ "loss": 3.9142,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "grad_norm": 0.9501475691795349,
43
+ "learning_rate": 3.937416087865917e-05,
44
+ "loss": 3.8441,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.096,
49
+ "grad_norm": 0.9516975283622742,
50
+ "learning_rate": 3.91002746699101e-05,
51
+ "loss": 3.7967,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.112,
56
+ "grad_norm": 0.8569780588150024,
57
+ "learning_rate": 3.877813950967087e-05,
58
+ "loss": 3.7618,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.128,
63
+ "grad_norm": 0.940584659576416,
64
+ "learning_rate": 3.8408569139313696e-05,
65
+ "loss": 3.6315,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.144,
70
+ "grad_norm": 0.9224157333374023,
71
+ "learning_rate": 3.799249712566837e-05,
72
+ "loss": 3.6187,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.16,
77
+ "grad_norm": 0.8730221390724182,
78
+ "learning_rate": 3.753097450275138e-05,
79
+ "loss": 3.5771,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.176,
84
+ "grad_norm": 0.8778759837150574,
85
+ "learning_rate": 3.7025167116762844e-05,
86
+ "loss": 3.5414,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.192,
91
+ "grad_norm": 1.054726004600525,
92
+ "learning_rate": 3.647635268105776e-05,
93
+ "loss": 3.5168,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.208,
98
+ "grad_norm": 0.9288316965103149,
99
+ "learning_rate": 3.5885917548531206e-05,
100
+ "loss": 3.4751,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.224,
105
+ "grad_norm": 1.053566813468933,
106
+ "learning_rate": 3.52553532095706e-05,
107
+ "loss": 3.487,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.24,
112
+ "grad_norm": 0.9158502817153931,
113
+ "learning_rate": 3.458625252442156e-05,
114
+ "loss": 3.4344,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.256,
119
+ "grad_norm": 1.1394481658935547,
120
+ "learning_rate": 3.388030569948466e-05,
121
+ "loss": 3.4369,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.272,
126
+ "grad_norm": 0.8391066789627075,
127
+ "learning_rate": 3.313929601770737e-05,
128
+ "loss": 3.3938,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.288,
133
+ "grad_norm": 0.8551831841468811,
134
+ "learning_rate": 3.23650953338566e-05,
135
+ "loss": 3.3531,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.304,
140
+ "grad_norm": 0.8429365754127502,
141
+ "learning_rate": 3.155965934605104e-05,
142
+ "loss": 3.3752,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.32,
147
+ "grad_norm": 0.998236358165741,
148
+ "learning_rate": 3.072502265549804e-05,
149
+ "loss": 3.3798,
150
+ "step": 2000
151
+ }
152
+ ],
153
+ "logging_steps": 100,
154
+ "max_steps": 6250,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 1,
157
+ "save_steps": 2000,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 5.4483807633408e+16,
171
+ "train_batch_size": 2,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff