Hugging Face's logo

davanstrien
/
dataset-rows-task-classifier

Text Classification
Transformers
Safetensors
lfm2
uv-script
hf-jobs
custom_code
Model card Files
xet
 Community
dataset-rows-task-classifier
File size: 4,173 Bytes
443fc75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
{
  "architectures": [
    "EncoderForSequenceClassification"
  ],
  "auto_map": {
    "AutoModel": "modeling_lfm2_bidirectional.Lfm2BidirectionalModel",
    "AutoModelForMaskedLM": "modeling_lfm2_bidirectional.Lfm2BidirectionalForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_encoder_seq_cls.EncoderForSequenceClassification"
  },
  "block_auto_adjust_ff_dim": true,
  "block_dim": 1024,
  "block_ffn_dim_multiplier": 1.0,
  "block_mlp_init_scale": 1.0,
  "block_multiple_of": 256,
  "block_norm_eps": 1e-05,
  "block_out_init_scale": 1.0,
  "block_use_swiglu": true,
  "block_use_xavier_init": true,
  "bos_token_id": 1,
  "classifier_thresholds": [
    0.35,
    0.15,
    0.2,
    0.15,
    0.15,
    0.4,
    0.1,
    0.15,
    0.2,
    0.1,
    0.2,
    0.3,
    0.2,
    0.35,
    0.3,
    0.25,
    0.55,
    0.5,
    0.3,
    0.05,
    0.4,
    0.25,
    0.4,
    0.3,
    0.2,
    0.35,
    0.25,
    0.45,
    0.3,
    0.25,
    0.25,
    0.1,
    0.1,
    0.2,
    0.15
  ],
  "conv_L_cache": 3,
  "conv_bias": false,
  "conv_dim": 1024,
  "conv_dim_out": 1024,
  "conv_use_xavier_init": true,
  "dtype": "float32",
  "eos_token_id": 7,
  "full_attn_idxs": null,
  "hidden_size": 1024,
  "id2label": {
    "0": "audio-classification",
    "1": "audio-to-audio",
    "10": "image-to-image",
    "11": "image-to-text",
    "12": "multiple-choice",
    "13": "object-detection",
    "14": "question-answering",
    "15": "reinforcement-learning",
    "16": "robotics",
    "17": "sentence-similarity",
    "18": "summarization",
    "19": "table-question-answering",
    "2": "automatic-speech-recognition",
    "20": "tabular-classification",
    "21": "tabular-regression",
    "22": "text-classification",
    "23": "text-generation",
    "24": "text-retrieval",
    "25": "text-to-image",
    "26": "text-to-speech",
    "27": "text-to-video",
    "28": "time-series-forecasting",
    "29": "token-classification",
    "3": "feature-extraction",
    "30": "translation",
    "31": "video-classification",
    "32": "video-text-to-text",
    "33": "visual-question-answering",
    "34": "zero-shot-classification",
    "4": "fill-mask",
    "5": "image-classification",
    "6": "image-feature-extraction",
    "7": "image-segmentation",
    "8": "image-text-to-text",
    "9": "image-to-3d"
  },
  "initializer_range": 0.02,
  "intermediate_size": 6656,
  "label2id": {
    "audio-classification": 0,
    "audio-to-audio": 1,
    "automatic-speech-recognition": 2,
    "feature-extraction": 3,
    "fill-mask": 4,
    "image-classification": 5,
    "image-feature-extraction": 6,
    "image-segmentation": 7,
    "image-text-to-text": 8,
    "image-to-3d": 9,
    "image-to-image": 10,
    "image-to-text": 11,
    "multiple-choice": 12,
    "object-detection": 13,
    "question-answering": 14,
    "reinforcement-learning": 15,
    "robotics": 16,
    "sentence-similarity": 17,
    "summarization": 18,
    "table-question-answering": 19,
    "tabular-classification": 20,
    "tabular-regression": 21,
    "text-classification": 22,
    "text-generation": 23,
    "text-retrieval": 24,
    "text-to-image": 25,
    "text-to-speech": 26,
    "text-to-video": 27,
    "time-series-forecasting": 28,
    "token-classification": 29,
    "translation": 30,
    "video-classification": 31,
    "video-text-to-text": 32,
    "visual-question-answering": 33,
    "zero-shot-classification": 34
  },
  "layer_types": [
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv"
  ],
  "max_position_embeddings": 128000,
  "model_type": "lfm2",
  "norm_eps": 1e-05,
  "num_attention_heads": 16,
  "num_heads": 16,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "problem_type": "multi_label_classification",
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.14.1",
  "use_cache": false,
  "use_pos_enc": true,
  "vocab_size": 65536
}