Hugging Face's logo

nimeshpiyumal
/
genux-ai-beta

TensorBoard
Safetensors
English
gpt2
generated
nimesh
genux
chatbot
Model card Files Metrics Community
nimeshpiyumal commited on
Commit
0824e1f
·
verified ·
1 Parent(s): c5414d6

Added Genux AI by Nimesh Piyumal

Browse files
Files changed (17) hide show
  1. added_tokens.json +13 -0
  2. checkpoint-150/config.json +39 -0
  3. checkpoint-150/generation_config.json +6 -0
  4. checkpoint-150/model.safetensors +3 -0
  5. checkpoint-150/optimizer.pt +3 -0
  6. checkpoint-150/rng_state.pth +3 -0
  7. checkpoint-150/scheduler.pt +3 -0
  8. checkpoint-150/trainer_state.json +54 -0
  9. checkpoint-150/training_args.bin +3 -0
  10. config.json +39 -0
  11. generation_config.json +6 -0
  12. merges.txt +0 -0
  13. model.safetensors +3 -0
  14. runs/Apr05_08-17-34_2dca798b4ed9/events.out.tfevents.1743841055.2dca798b4ed9.264.2 +3 -0
  15. special_tokens_map.json +102 -0
  16. tokenizer_config.json +123 -0
  17. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<<coding_philosophy>>": 50264,
3
+ "<<collabs>>": 50266,
4
+ "<<intro>>": 50263,
5
+ "<<projects>>": 50265,
6
+ "<<signature>>": 50267,
7
+ "<ai>": 50262,
8
+ "<dev>": 50259,
9
+ "<java>": 50261,
10
+ "<nimesh>": 50258,
11
+ "<pad>": 50257,
12
+ "<python>": 50260
13
+ }
checkpoint-150/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.48.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50262
39
+ }
checkpoint-150/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.3"
6
+ }
checkpoint-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a5639a503aed50b95e763b9b743bcef507fde2ed6f283df234bfec4c771b1c
3
+ size 497789568
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4974c20a51cdaa4b2b7bfb437e51a7edf7f56605f5fe47b014daeb579e8ed53c
3
+ size 995673018
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ef36938e68000886fac32f0e9485e9d380e40e95a3b765b2f937c5eeb98447
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1320cc0c91c904e1b37627facbc7bdd09ad072c5e9a4fe376e5569a5cdf3a73
3
+ size 1064
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 16.666666666666668,
13
+ "grad_norm": 2.5736591815948486,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 1.175,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 33.333333333333336,
20
+ "grad_norm": 9.538090705871582,
21
+ "learning_rate": 1.6666666666666667e-05,
22
+ "loss": 0.3005,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 50.0,
27
+ "grad_norm": 0.5207849144935608,
28
+ "learning_rate": 0.0,
29
+ "loss": 0.2636,
30
+ "step": 150
31
+ }
32
+ ],
33
+ "logging_steps": 50,
34
+ "max_steps": 150,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 50,
37
+ "save_steps": 200,
38
+ "stateful_callbacks": {
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": true
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 9798451200000.0,
51
+ "train_batch_size": 2,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defb35e1c964ea5b6b7d4629845332b0be5408eca53f44e142b48cdeeca4e3ca
3
+ size 5304
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.48.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50268
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.3"
6
+ }
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 sha256:148906f03ee8316e06789ccc928ee75f8c0d037aa85cd0c53287a1a3dc657500
3
+ size 497808000
runs/Apr05_08-17-34_2dca798b4ed9/events.out.tfevents.1743841055.2dca798b4ed9.264.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b948b065fb4503c5e0a2363bfb9cb083df2094d5dae25f839bc8f8407f6324b6
3
+ size 6241
special_tokens_map.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<nimesh>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<dev>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<python>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<java>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<ai>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<<intro>>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<<coding_philosophy>>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<<projects>>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<<collabs>>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<<signature>>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
+ "bos_token": {
75
+ "content": "<|endoftext|>",
76
+ "lstrip": false,
77
+ "normalized": true,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "eos_token": {
82
+ "content": "<|endoftext|>",
83
+ "lstrip": false,
84
+ "normalized": true,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "pad_token": {
89
+ "content": "<pad>",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "unk_token": {
96
+ "content": "<|endoftext|>",
97
+ "lstrip": false,
98
+ "normalized": true,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ }
102
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<nimesh>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50259": {
30
+ "content": "<dev>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<python>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "<java>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<ai>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "<<intro>>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50264": {
70
+ "content": "<<coding_philosophy>>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50265": {
78
+ "content": "<<projects>>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50266": {
86
+ "content": "<<collabs>>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50267": {
94
+ "content": "<<signature>>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "<nimesh>",
104
+ "<dev>",
105
+ "<python>",
106
+ "<java>",
107
+ "<ai>",
108
+ "<<intro>>",
109
+ "<<coding_philosophy>>",
110
+ "<<projects>>",
111
+ "<<collabs>>",
112
+ "<<signature>>"
113
+ ],
114
+ "bos_token": "<|endoftext|>",
115
+ "clean_up_tokenization_spaces": false,
116
+ "eos_token": "<|endoftext|>",
117
+ "errors": "replace",
118
+ "extra_special_tokens": {},
119
+ "model_max_length": 1024,
120
+ "pad_token": "<pad>",
121
+ "tokenizer_class": "GPT2Tokenizer",
122
+ "unk_token": "<|endoftext|>"
123
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff