Hugging Face's logo

dima806
/
human-vs-llm-generated-text-detection-distilbert

Text Classification
Transformers
Safetensors
distilbert
Inference Endpoints
Model card Files Community
3
dima806 commited on
Commit
9e87d75
·
verified ·
1 Parent(s): 7ed3d55

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. checkpoint-88754/config.json +155 -0
  3. checkpoint-88754/model.safetensors +3 -0
  4. checkpoint-88754/optimizer.pt +3 -0
  5. checkpoint-88754/rng_state.pth +3 -0
  6. checkpoint-88754/scheduler.pt +3 -0
  7. checkpoint-88754/trainer_state.json +3 -0
  8. checkpoint-88754/training_args.bin +3 -0
  9. config.json +155 -0
  10. model.safetensors +3 -0
  11. training_args.bin +3 -0
  12. vocab.txt +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-88754/trainer_state.json filter=lfs diff=lfs merge=lfs -text
checkpoint-88754/config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Bloom-7B",
13
+ "1": "Claude-Instant-v1",
14
+ "2": "Claude-v1",
15
+ "3": "Cohere-Command",
16
+ "4": "Dolphin-2.5-Mixtral-8x7B",
17
+ "5": "Dolphin-Mixtral-8x7B",
18
+ "6": "Falcon-180B",
19
+ "7": "Flan-T5-Base",
20
+ "8": "Flan-T5-Large",
21
+ "9": "Flan-T5-Small",
22
+ "10": "Flan-T5-XL",
23
+ "11": "Flan-T5-XXL",
24
+ "12": "GLM-130B",
25
+ "13": "GPT-3.5",
26
+ "14": "GPT-4",
27
+ "15": "GPT-J",
28
+ "16": "GPT-NeoX",
29
+ "17": "Gemini-Pro",
30
+ "18": "Goliath-120B",
31
+ "19": "Human",
32
+ "20": "LLaMA-13B",
33
+ "21": "LLaMA-2-70B",
34
+ "22": "LLaMA-2-7B",
35
+ "23": "LLaMA-30B",
36
+ "24": "LLaMA-65B",
37
+ "25": "LLaMA-7B",
38
+ "26": "LZLV-70B",
39
+ "27": "Mistral-7B",
40
+ "28": "Mistral-7B-OpenOrca",
41
+ "29": "Mixtral-8x7B",
42
+ "30": "MythoMax-L2-13B",
43
+ "31": "Neural-Chat-7B",
44
+ "32": "Noromaid-20B",
45
+ "33": "Nous-Capybara-34B",
46
+ "34": "Nous-Capybara-7B",
47
+ "35": "Nous-Hermes-LLaMA-2-13B",
48
+ "36": "Nous-Hermes-LLaMA-2-70B",
49
+ "37": "OPT-1.3B",
50
+ "38": "OPT-125M",
51
+ "39": "OPT-13B",
52
+ "40": "OPT-2.7B",
53
+ "41": "OPT-30B",
54
+ "42": "OPT-350M",
55
+ "43": "OPT-6.7B",
56
+ "44": "OpenChat-3.5",
57
+ "45": "OpenHermes-2-Mistral-7B",
58
+ "46": "OpenHermes-2.5-Mistral-7B",
59
+ "47": "PaLM-2",
60
+ "48": "Psyfighter-13B",
61
+ "49": "Psyfighter-2-13B",
62
+ "50": "RWKV-5-World-3B",
63
+ "51": "StripedHyena-Nous-7B",
64
+ "52": "T0-11B",
65
+ "53": "T0-3B",
66
+ "54": "Text-Ada-001",
67
+ "55": "Text-Babbage-001",
68
+ "56": "Text-Curie-001",
69
+ "57": "Text-Davinci-001",
70
+ "58": "Text-Davinci-002",
71
+ "59": "Text-Davinci-003",
72
+ "60": "Toppy-M-7B",
73
+ "61": "Unknown",
74
+ "62": "YI-34B"
75
+ },
76
+ "initializer_range": 0.02,
77
+ "label2id": {
78
+ "Bloom-7B": 0,
79
+ "Claude-Instant-v1": 1,
80
+ "Claude-v1": 2,
81
+ "Cohere-Command": 3,
82
+ "Dolphin-2.5-Mixtral-8x7B": 4,
83
+ "Dolphin-Mixtral-8x7B": 5,
84
+ "Falcon-180B": 6,
85
+ "Flan-T5-Base": 7,
86
+ "Flan-T5-Large": 8,
87
+ "Flan-T5-Small": 9,
88
+ "Flan-T5-XL": 10,
89
+ "Flan-T5-XXL": 11,
90
+ "GLM-130B": 12,
91
+ "GPT-3.5": 13,
92
+ "GPT-4": 14,
93
+ "GPT-J": 15,
94
+ "GPT-NeoX": 16,
95
+ "Gemini-Pro": 17,
96
+ "Goliath-120B": 18,
97
+ "Human": 19,
98
+ "LLaMA-13B": 20,
99
+ "LLaMA-2-70B": 21,
100
+ "LLaMA-2-7B": 22,
101
+ "LLaMA-30B": 23,
102
+ "LLaMA-65B": 24,
103
+ "LLaMA-7B": 25,
104
+ "LZLV-70B": 26,
105
+ "Mistral-7B": 27,
106
+ "Mistral-7B-OpenOrca": 28,
107
+ "Mixtral-8x7B": 29,
108
+ "MythoMax-L2-13B": 30,
109
+ "Neural-Chat-7B": 31,
110
+ "Noromaid-20B": 32,
111
+ "Nous-Capybara-34B": 33,
112
+ "Nous-Capybara-7B": 34,
113
+ "Nous-Hermes-LLaMA-2-13B": 35,
114
+ "Nous-Hermes-LLaMA-2-70B": 36,
115
+ "OPT-1.3B": 37,
116
+ "OPT-125M": 38,
117
+ "OPT-13B": 39,
118
+ "OPT-2.7B": 40,
119
+ "OPT-30B": 41,
120
+ "OPT-350M": 42,
121
+ "OPT-6.7B": 43,
122
+ "OpenChat-3.5": 44,
123
+ "OpenHermes-2-Mistral-7B": 45,
124
+ "OpenHermes-2.5-Mistral-7B": 46,
125
+ "PaLM-2": 47,
126
+ "Psyfighter-13B": 48,
127
+ "Psyfighter-2-13B": 49,
128
+ "RWKV-5-World-3B": 50,
129
+ "StripedHyena-Nous-7B": 51,
130
+ "T0-11B": 52,
131
+ "T0-3B": 53,
132
+ "Text-Ada-001": 54,
133
+ "Text-Babbage-001": 55,
134
+ "Text-Curie-001": 56,
135
+ "Text-Davinci-001": 57,
136
+ "Text-Davinci-002": 58,
137
+ "Text-Davinci-003": 59,
138
+ "Toppy-M-7B": 60,
139
+ "Unknown": 61,
140
+ "YI-34B": 62
141
+ },
142
+ "max_position_embeddings": 512,
143
+ "model_type": "distilbert",
144
+ "n_heads": 12,
145
+ "n_layers": 6,
146
+ "output_past": true,
147
+ "pad_token_id": 0,
148
+ "qa_dropout": 0.1,
149
+ "seq_classif_dropout": 0.2,
150
+ "sinusoidal_pos_embds": false,
151
+ "tie_weights_": true,
152
+ "torch_dtype": "float32",
153
+ "transformers_version": "4.36.2",
154
+ "vocab_size": 28996
155
+ }
checkpoint-88754/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e9c5014220dcfd020a8ab90f4078470fdddf8775ee4c9fcc94898f4a9ad6af
3
+ size 263332332
checkpoint-88754/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385920b9c59f8e359d4e0c68e0190b76a49e57cf5d2a5fb13e08f37c67969b5f
3
+ size 526726277
checkpoint-88754/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63980bdbeea41aa7b307b2a4cdff1e0364f38aa961928a7d20552cfd8957d01a
3
+ size 14575
checkpoint-88754/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a559e4d0003d8c22de61013fa9b1befcf261281f18f411cc229fc25852820e18
3
+ size 627
checkpoint-88754/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009125b4d3adf3987ee2127fd373d533916a1bebc47adb39fa8d0489a0eedc54
3
+ size 10837780
checkpoint-88754/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc53e77e890feea3faf903a787e75efb3eb599a1c8db140efa31d7579162936c
3
+ size 4219
config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Bloom-7B",
13
+ "1": "Claude-Instant-v1",
14
+ "2": "Claude-v1",
15
+ "3": "Cohere-Command",
16
+ "4": "Dolphin-2.5-Mixtral-8x7B",
17
+ "5": "Dolphin-Mixtral-8x7B",
18
+ "6": "Falcon-180B",
19
+ "7": "Flan-T5-Base",
20
+ "8": "Flan-T5-Large",
21
+ "9": "Flan-T5-Small",
22
+ "10": "Flan-T5-XL",
23
+ "11": "Flan-T5-XXL",
24
+ "12": "GLM-130B",
25
+ "13": "GPT-3.5",
26
+ "14": "GPT-4",
27
+ "15": "GPT-J",
28
+ "16": "GPT-NeoX",
29
+ "17": "Gemini-Pro",
30
+ "18": "Goliath-120B",
31
+ "19": "Human",
32
+ "20": "LLaMA-13B",
33
+ "21": "LLaMA-2-70B",
34
+ "22": "LLaMA-2-7B",
35
+ "23": "LLaMA-30B",
36
+ "24": "LLaMA-65B",
37
+ "25": "LLaMA-7B",
38
+ "26": "LZLV-70B",
39
+ "27": "Mistral-7B",
40
+ "28": "Mistral-7B-OpenOrca",
41
+ "29": "Mixtral-8x7B",
42
+ "30": "MythoMax-L2-13B",
43
+ "31": "Neural-Chat-7B",
44
+ "32": "Noromaid-20B",
45
+ "33": "Nous-Capybara-34B",
46
+ "34": "Nous-Capybara-7B",
47
+ "35": "Nous-Hermes-LLaMA-2-13B",
48
+ "36": "Nous-Hermes-LLaMA-2-70B",
49
+ "37": "OPT-1.3B",
50
+ "38": "OPT-125M",
51
+ "39": "OPT-13B",
52
+ "40": "OPT-2.7B",
53
+ "41": "OPT-30B",
54
+ "42": "OPT-350M",
55
+ "43": "OPT-6.7B",
56
+ "44": "OpenChat-3.5",
57
+ "45": "OpenHermes-2-Mistral-7B",
58
+ "46": "OpenHermes-2.5-Mistral-7B",
59
+ "47": "PaLM-2",
60
+ "48": "Psyfighter-13B",
61
+ "49": "Psyfighter-2-13B",
62
+ "50": "RWKV-5-World-3B",
63
+ "51": "StripedHyena-Nous-7B",
64
+ "52": "T0-11B",
65
+ "53": "T0-3B",
66
+ "54": "Text-Ada-001",
67
+ "55": "Text-Babbage-001",
68
+ "56": "Text-Curie-001",
69
+ "57": "Text-Davinci-001",
70
+ "58": "Text-Davinci-002",
71
+ "59": "Text-Davinci-003",
72
+ "60": "Toppy-M-7B",
73
+ "61": "Unknown",
74
+ "62": "YI-34B"
75
+ },
76
+ "initializer_range": 0.02,
77
+ "label2id": {
78
+ "Bloom-7B": 0,
79
+ "Claude-Instant-v1": 1,
80
+ "Claude-v1": 2,
81
+ "Cohere-Command": 3,
82
+ "Dolphin-2.5-Mixtral-8x7B": 4,
83
+ "Dolphin-Mixtral-8x7B": 5,
84
+ "Falcon-180B": 6,
85
+ "Flan-T5-Base": 7,
86
+ "Flan-T5-Large": 8,
87
+ "Flan-T5-Small": 9,
88
+ "Flan-T5-XL": 10,
89
+ "Flan-T5-XXL": 11,
90
+ "GLM-130B": 12,
91
+ "GPT-3.5": 13,
92
+ "GPT-4": 14,
93
+ "GPT-J": 15,
94
+ "GPT-NeoX": 16,
95
+ "Gemini-Pro": 17,
96
+ "Goliath-120B": 18,
97
+ "Human": 19,
98
+ "LLaMA-13B": 20,
99
+ "LLaMA-2-70B": 21,
100
+ "LLaMA-2-7B": 22,
101
+ "LLaMA-30B": 23,
102
+ "LLaMA-65B": 24,
103
+ "LLaMA-7B": 25,
104
+ "LZLV-70B": 26,
105
+ "Mistral-7B": 27,
106
+ "Mistral-7B-OpenOrca": 28,
107
+ "Mixtral-8x7B": 29,
108
+ "MythoMax-L2-13B": 30,
109
+ "Neural-Chat-7B": 31,
110
+ "Noromaid-20B": 32,
111
+ "Nous-Capybara-34B": 33,
112
+ "Nous-Capybara-7B": 34,
113
+ "Nous-Hermes-LLaMA-2-13B": 35,
114
+ "Nous-Hermes-LLaMA-2-70B": 36,
115
+ "OPT-1.3B": 37,
116
+ "OPT-125M": 38,
117
+ "OPT-13B": 39,
118
+ "OPT-2.7B": 40,
119
+ "OPT-30B": 41,
120
+ "OPT-350M": 42,
121
+ "OPT-6.7B": 43,
122
+ "OpenChat-3.5": 44,
123
+ "OpenHermes-2-Mistral-7B": 45,
124
+ "OpenHermes-2.5-Mistral-7B": 46,
125
+ "PaLM-2": 47,
126
+ "Psyfighter-13B": 48,
127
+ "Psyfighter-2-13B": 49,
128
+ "RWKV-5-World-3B": 50,
129
+ "StripedHyena-Nous-7B": 51,
130
+ "T0-11B": 52,
131
+ "T0-3B": 53,
132
+ "Text-Ada-001": 54,
133
+ "Text-Babbage-001": 55,
134
+ "Text-Curie-001": 56,
135
+ "Text-Davinci-001": 57,
136
+ "Text-Davinci-002": 58,
137
+ "Text-Davinci-003": 59,
138
+ "Toppy-M-7B": 60,
139
+ "Unknown": 61,
140
+ "YI-34B": 62
141
+ },
142
+ "max_position_embeddings": 512,
143
+ "model_type": "distilbert",
144
+ "n_heads": 12,
145
+ "n_layers": 6,
146
+ "output_past": true,
147
+ "pad_token_id": 0,
148
+ "qa_dropout": 0.1,
149
+ "seq_classif_dropout": 0.2,
150
+ "sinusoidal_pos_embds": false,
151
+ "tie_weights_": true,
152
+ "torch_dtype": "float32",
153
+ "transformers_version": "4.36.2",
154
+ "vocab_size": 28996
155
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e9c5014220dcfd020a8ab90f4078470fdddf8775ee4c9fcc94898f4a9ad6af
3
+ size 263332332
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc53e77e890feea3faf903a787e75efb3eb599a1c8db140efa31d7579162936c
3
+ size 4219
vocab.txt ADDED
The diff for this file is too large to render. See raw diff