Hugging Face's logo

Wonder-Griffin
/
JudgeLLM2

Text Classification
Transformers
Safetensors
English
gpt2
text-generation-inference
causal-language-model
conversational
question-answering
Model card Files
xet
Community
Wonder-Griffin commited on
Commit
d0710aa
·
verified ·
1 Parent(s): 58a9cc1

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +102 -102
config.json CHANGED
@@ -1,102 +1,102 @@
1
- {
2
- "_name_": "Judge-GPT2",
3
- "_name_or_path": "C:/Users/wonde/text-generation-ai/JudgeLLM2/checkpoint-1719",
4
- "activation_function": "gelu_new",
5
- "architectures": [
6
- "GPT2LMHeadModel"
7
- ],
8
- "attn_pdrop": 0.1,
9
- "batch_size": 32,
10
- "bias": true,
11
- "block_size": 512,
12
- "bos_token_id": 50256,
13
- "dim_feedforward": 3072,
14
- "dropout": 0.1,
15
- "embd_pdrop": 0.1,
16
- "eos_token_id": 50256,
17
- "ff_expansion_factor": 4,
18
- "hidden_act": "gelu",
19
- "id2label": {
20
- "0": "LABEL_0",
21
- "1": "LABEL_1",
22
- "2": "LABEL_2",
23
- "3": "LABEL_3",
24
- "4": "LABEL_4"
25
- },
26
- "inference_mode": true,
27
- "initializer_range": 0.02,
28
- "label2id": {
29
- "LABEL_0": 0,
30
- "LABEL_1": 1,
31
- "LABEL_2": 2,
32
- "LABEL_3": 3,
33
- "LABEL_4": 4
34
- },
35
- "label_smoothing": 0.1,
36
- "layer_norm_epsilon": 1e-05,
37
- "learning_rate": 0.0003,
38
- "log_interval": 100,
39
- "max_grad_norm": 1.0,
40
- "model_type": "gpt2",
41
- "n_embd": 768,
42
- "n_head": 12,
43
- "n_inner": null,
44
- "n_layer": 12,
45
- "n_positions": 512,
46
- "output_dir": "C:/Users/wonde/output",
47
- "pretrained_weights": "Wonder-Griffin/Judge-GPT2",
48
- "reorder_and_upcast_attn": false,
49
- "resid_pdrop": 0.1,
50
- "scale_attn_by_inverse_layer_idx": false,
51
- "scale_attn_weights": true,
52
- "summary_activation": null,
53
- "summary_first_dropout": 0.1,
54
- "summary_proj_to_labels": true,
55
- "summary_type": "cls_index",
56
- "summary_use_proj": true,
57
- "task_heads": {
58
- "classifier_head": {
59
- "params": {
60
- "num_labels": 5
61
- },
62
- "type": "JudgeClassifier"
63
- },
64
- "lm_head": {
65
- "params": {
66
- "vocab_size": 50257
67
- },
68
- "type": "JudgeCasualLMHead"
69
- },
70
- "qa_head": {
71
- "params": {
72
- "num_labels": 2
73
- },
74
- "type": "JudgeWithQA"
75
- }
76
- },
77
- "task_specific_params": {
78
- "question-answering": {
79
- "max_answer_length": 100
80
- },
81
- "sequence-classification": {
82
- "eval_steps": 500
83
- },
84
- "text-generation": {
85
- "do_sample": true,
86
- "max_length": 100
87
- }
88
- },
89
- "tokenizer": {
90
- "params": {
91
- "vocab_size": 50257
92
- },
93
- "type": "AutoTokenizer"
94
- },
95
- "torch_dtype": "float32",
96
- "total_steps": 10000,
97
- "transformers_version": "4.43.3",
98
- "use_cache": true,
99
- "vocab_size": 50257,
100
- "warmup_steps": 1000,
101
- "weight_decay": 0.01
102
- }
 
1
+ {
2
+ "_name_": "Judge-GPT2",
3
+ "_name_or_path": "Wonder-Griffin/JudgeLLM2",
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPTForCasualLM"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "batch_size": 32,
10
+ "bias": true,
11
+ "block_size": 512,
12
+ "bos_token_id": 50256,
13
+ "dim_feedforward": 3072,
14
+ "dropout": 0.1,
15
+ "embd_pdrop": 0.1,
16
+ "eos_token_id": 50256,
17
+ "ff_expansion_factor": 4,
18
+ "hidden_act": "gelu",
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1",
22
+ "2": "LABEL_2",
23
+ "3": "LABEL_3",
24
+ "4": "LABEL_4"
25
+ },
26
+ "inference_mode": true,
27
+ "initializer_range": 0.02,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_2": 2,
32
+ "LABEL_3": 3,
33
+ "LABEL_4": 4
34
+ },
35
+ "label_smoothing": 0.1,
36
+ "layer_norm_epsilon": 1e-05,
37
+ "learning_rate": 0.0003,
38
+ "log_interval": 100,
39
+ "max_grad_norm": 1.0,
40
+ "model_type": "gpt2",
41
+ "n_embd": 768,
42
+ "n_head": 12,
43
+ "n_inner": null,
44
+ "n_layer": 12,
45
+ "n_positions": 512,
46
+ "output_dir": "C:/Users/wonde/output",
47
+ "pretrained_weights": "Wonder-Griffin/JudgeLLM2",
48
+ "reorder_and_upcast_attn": false,
49
+ "resid_pdrop": 0.1,
50
+ "scale_attn_by_inverse_layer_idx": false,
51
+ "scale_attn_weights": true,
52
+ "summary_activation": null,
53
+ "summary_first_dropout": 0.1,
54
+ "summary_proj_to_labels": true,
55
+ "summary_type": "cls_index",
56
+ "summary_use_proj": true,
57
+ "task_heads": {
58
+ "classifier_head": {
59
+ "params": {
60
+ "num_labels": 5
61
+ },
62
+ "type": "JudgeClassifier"
63
+ },
64
+ "lm_head": {
65
+ "params": {
66
+ "vocab_size": 50257
67
+ },
68
+ "type": "JudgeCasualLMHead"
69
+ },
70
+ "qa_head": {
71
+ "params": {
72
+ "num_labels": 2
73
+ },
74
+ "type": "JudgeWithQA"
75
+ }
76
+ },
77
+ "task_specific_params": {
78
+ "question-answering": {
79
+ "max_answer_length": 100
80
+ },
81
+ "sequence-classification": {
82
+ "eval_steps": 500
83
+ },
84
+ "text-generation": {
85
+ "do_sample": true,
86
+ "max_length": 100
87
+ }
88
+ },
89
+ "tokenizer": {
90
+ "params": {
91
+ "vocab_size": 50257
92
+ },
93
+ "type": "AutoTokenizer"
94
+ },
95
+ "torch_dtype": "float32",
96
+ "total_steps": 10000,
97
+ "transformers_version": "4.43.3",
98
+ "use_cache": true,
99
+ "vocab_size": 50257,
100
+ "warmup_steps": 1000,
101
+ "weight_decay": 0.01
102
+ }