Hugging Face's logo

zheng520
/
LLM-as-a-Fuzzy-Judge

Safetensors
Model card Files
xet
 Community
zheng520 commited on
Commit
9637a89
·
verified ·
1 Parent(s): 2cebaed

Upload folder using huggingface_hub

Browse files
Files changed (44) hide show
  1. distraction/best_model/added_tokens.json +3 -0
  2. distraction/best_model/config.json +37 -0
  3. distraction/best_model/merges.txt +0 -0
  4. distraction/best_model/model.safetensors +3 -0
  5. distraction/best_model/model.safetensors.index.json +262 -0
  6. distraction/best_model/special_tokens_map.json +37 -0
  7. distraction/best_model/spm.model +3 -0
  8. distraction/best_model/tokenizer.json +0 -0
  9. distraction/best_model/tokenizer_config.json +65 -0
  10. distraction/best_model/vocab.json +0 -0
  11. distraction/best_model/vocab.txt +0 -0
  12. ethics/best_model/added_tokens.json +3 -0
  13. ethics/best_model/config.json +39 -0
  14. ethics/best_model/merges.txt +0 -0
  15. ethics/best_model/model.safetensors +3 -0
  16. ethics/best_model/model.safetensors.index.json +262 -0
  17. ethics/best_model/special_tokens_map.json +37 -0
  18. ethics/best_model/spm.model +3 -0
  19. ethics/best_model/tokenizer.json +0 -0
  20. ethics/best_model/tokenizer_config.json +65 -0
  21. ethics/best_model/vocab.json +0 -0
  22. ethics/best_model/vocab.txt +0 -0
  23. professionalism/best_model/added_tokens.json +3 -0
  24. professionalism/best_model/config.json +35 -0
  25. professionalism/best_model/merges.txt +0 -0
  26. professionalism/best_model/model.safetensors +3 -0
  27. professionalism/best_model/model.safetensors.index.json +262 -0
  28. professionalism/best_model/special_tokens_map.json +37 -0
  29. professionalism/best_model/spm.model +3 -0
  30. professionalism/best_model/tokenizer.json +0 -0
  31. professionalism/best_model/tokenizer_config.json +65 -0
  32. professionalism/best_model/vocab.json +0 -0
  33. professionalism/best_model/vocab.txt +0 -0
  34. relevance/best_model/added_tokens.json +3 -0
  35. relevance/best_model/config.json +35 -0
  36. relevance/best_model/merges.txt +0 -0
  37. relevance/best_model/model.safetensors +3 -0
  38. relevance/best_model/model.safetensors.index.json +262 -0
  39. relevance/best_model/special_tokens_map.json +37 -0
  40. relevance/best_model/spm.model +3 -0
  41. relevance/best_model/tokenizer.json +0 -0
  42. relevance/best_model/tokenizer_config.json +65 -0
  43. relevance/best_model/vocab.json +0 -0
  44. relevance/best_model/vocab.txt +0 -0
distraction/best_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
distraction/best_model/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.51.3",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 28996
37
+ }
distraction/best_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
distraction/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b99e6ccee4497cdfeee032d22f6dd6b85c0284e8f5d30d09e144955ab3d9f3
3
+ size 433276920
distraction/best_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851048448
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
distraction/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
distraction/best_model/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
distraction/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distraction/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
distraction/best_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
distraction/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
ethics/best_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
ethics/best_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3,
24
+ "LABEL_4": 4
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.51.3",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 28996
39
+ }
ethics/best_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ethics/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8307d54914145c784450f9bd4f24811e1e8a8d2ccb4d4efba7e4a1c1928cc99
3
+ size 433279996
ethics/best_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851060736
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
ethics/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
ethics/best_model/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
ethics/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ethics/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
ethics/best_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
ethics/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
professionalism/best_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
professionalism/best_model/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.3",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
professionalism/best_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
professionalism/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55d2d799d52ded157193df4f34fd2ff60574fd622912dd445df9a7164c6720d
3
+ size 433273844
professionalism/best_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851036160
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
professionalism/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
professionalism/best_model/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
professionalism/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
professionalism/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
professionalism/best_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
professionalism/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
relevance/best_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
relevance/best_model/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.3",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
relevance/best_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
relevance/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114f65493bbd60e19b0a13e210e4e018328f40de4aef58ded0c20b865e20e03c
3
+ size 433273844
relevance/best_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851036160
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
relevance/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
relevance/best_model/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
relevance/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
relevance/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
relevance/best_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
relevance/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff