Hugging Face's logo

Yuto2007
/
tahoe-celltype-classifier

Safetensors
tahoe_x1
Model card Files
xet
Community
Yuto2007 commited on
Commit
8bfaea4
·
verified ·
1 Parent(s): ae394f3

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. classification_report.txt +57 -0
  2. collator_config.json +15 -0
  3. config.json +168 -0
  4. gene_order.npy +3 -0
  5. label_map.json +50 -0
  6. model.safetensors +3 -0
  7. vocab.json +0 -0
classification_report.txt ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ B cell 0.96 0.98 0.97 5679
4
+ CD1c-positive myeloid dendritic cell 0.83 0.91 0.87 4704
5
+ CD4-positive, alpha-beta T cell 0.90 0.95 0.92 12405
6
+ CD8-positive, alpha-beta T cell 0.88 0.94 0.91 17046
7
+ T cell 0.86 0.93 0.89 586
8
+ acinar cell 0.80 0.93 0.86 270
9
+ alveolar adventitial fibroblast 0.89 0.94 0.92 3489
10
+ alveolar macrophage 0.92 0.95 0.93 41444
11
+ alveolar type 1 fibroblast cell 0.92 0.95 0.93 5749
12
+ bronchial goblet cell 0.81 0.84 0.82 339
13
+ bronchus fibroblast of lung 0.68 0.80 0.73 1313
14
+ brush cell of tracheobronchial tree 0.63 0.89 0.74 96
15
+ capillary endothelial cell 0.91 0.96 0.93 9687
16
+ classical monocyte 0.87 0.93 0.90 9747
17
+ club cell 0.87 0.90 0.89 7555
18
+ conventional dendritic cell 0.81 0.97 0.89 217
19
+ dendritic cell 0.89 0.95 0.92 354
20
+ elicited macrophage 0.77 0.85 0.81 13237
21
+ endothelial cell of lymphatic vessel 0.88 0.96 0.92 1960
22
+ epithelial cell of lower respiratory tract 0.78 0.93 0.85 1669
23
+ fibroblast 0.76 0.85 0.80 164
24
+ hematopoietic stem cell 0.75 1.00 0.86 9
25
+ ionocyte 0.93 0.97 0.95 270
26
+ lung macrophage 0.79 0.84 0.81 1248
27
+ lung pericyte 0.90 0.94 0.92 1752
28
+ mast cell 0.99 0.99 0.99 3198
29
+ mesothelial cell 0.86 0.99 0.92 339
30
+ mucus secreting cell 0.88 0.97 0.92 214
31
+ multiciliated columnar cell of tracheobronchial tree 0.97 0.98 0.98 16961
32
+ multiciliated epithelial cell 0.91 0.95 0.93 1113
33
+ myofibroblast cell 0.76 0.86 0.81 289
34
+ nasal mucosa goblet cell 0.89 0.93 0.91 10854
35
+ natural killer cell 0.93 0.97 0.95 7266
36
+ non-classical monocyte 0.89 0.91 0.90 3939
37
+ plasma cell 0.98 0.98 0.98 4967
38
+ plasmacytoid dendritic cell 0.95 0.98 0.97 553
39
+ pulmonary alveolar epithelial cell 0.70 0.75 0.73 272
40
+ pulmonary alveolar type 1 cell 0.94 0.97 0.95 4846
41
+ pulmonary alveolar type 2 cell 0.97 0.98 0.98 23507
42
+ pulmonary artery endothelial cell 0.91 0.95 0.93 2209
43
+ pulmonary neuroendocrine cell 0.92 0.94 0.93 49
44
+ respiratory basal cell 0.90 0.95 0.93 17856
45
+ respiratory tract hillock cell 0.86 0.86 0.86 835
46
+ serous secreting cell 0.85 0.93 0.89 376
47
+ smooth muscle cell 0.65 0.85 0.74 268
48
+ stromal cell 0.71 0.82 0.76 83
49
+ tracheobronchial goblet cell 0.81 0.88 0.84 178
50
+ tracheobronchial serous cell 0.88 0.90 0.89 416
51
+ tracheobronchial smooth muscle cell 0.82 0.90 0.86 2501
52
+ unknown 0.87 0.76 0.81 93497
53
+ vein endothelial cell 0.88 0.94 0.91 4793
54
+
55
+ accuracy 0.89 342368
56
+ macro avg 0.86 0.92 0.89 342368
57
+ weighted avg 0.89 0.89 0.89 342368
collator_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_mlm": true,
3
+ "num_bins": 51,
4
+ "sampling": true,
5
+ "pad_value": -2,
6
+ "data_style": "both",
7
+ "do_binning": true,
8
+ "do_padding": true,
9
+ "mask_value": -1,
10
+ "max_length": 1024,
11
+ "right_binning": false,
12
+ "mlm_probability": 0.5,
13
+ "use_junk_tokens": false,
14
+ "pad_token_id": 0
15
+ }
config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "output_attentions": false,
5
+ "torchscript": false,
6
+ "torch_dtype": null,
7
+ "use_bfloat16": false,
8
+ "tf_legacy_loss": false,
9
+ "pruned_heads": {},
10
+ "tie_word_embeddings": true,
11
+ "chunk_size_feed_forward": 0,
12
+ "is_encoder_decoder": false,
13
+ "is_decoder": false,
14
+ "cross_attention_hidden_size": null,
15
+ "add_cross_attention": false,
16
+ "tie_encoder_decoder": false,
17
+ "max_length": 20,
18
+ "min_length": 0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "num_beams": 1,
22
+ "num_beam_groups": 1,
23
+ "diversity_penalty": 0.0,
24
+ "temperature": 1.0,
25
+ "top_k": 50,
26
+ "top_p": 1.0,
27
+ "typical_p": 1.0,
28
+ "repetition_penalty": 1.0,
29
+ "length_penalty": 1.0,
30
+ "no_repeat_ngram_size": 0,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "bad_words_ids": null,
33
+ "num_return_sequences": 1,
34
+ "output_scores": false,
35
+ "return_dict_in_generate": false,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "remove_invalid_values": false,
39
+ "exponential_decay_length_penalty": null,
40
+ "suppress_tokens": null,
41
+ "begin_suppress_tokens": null,
42
+ "architectures": null,
43
+ "finetuning_task": null,
44
+ "id2label": {
45
+ "0": "LABEL_0",
46
+ "1": "LABEL_1",
47
+ "2": "LABEL_2",
48
+ "3": "LABEL_3",
49
+ "4": "LABEL_4",
50
+ "5": "LABEL_5",
51
+ "6": "LABEL_6",
52
+ "7": "LABEL_7",
53
+ "8": "LABEL_8",
54
+ "9": "LABEL_9",
55
+ "10": "LABEL_10",
56
+ "11": "LABEL_11",
57
+ "12": "LABEL_12",
58
+ "13": "LABEL_13",
59
+ "14": "LABEL_14",
60
+ "15": "LABEL_15",
61
+ "16": "LABEL_16",
62
+ "17": "LABEL_17",
63
+ "18": "LABEL_18",
64
+ "19": "LABEL_19",
65
+ "20": "LABEL_20",
66
+ "21": "LABEL_21",
67
+ "22": "LABEL_22",
68
+ "23": "LABEL_23",
69
+ "24": "LABEL_24",
70
+ "25": "LABEL_25",
71
+ "26": "LABEL_26",
72
+ "27": "LABEL_27",
73
+ "28": "LABEL_28",
74
+ "29": "LABEL_29",
75
+ "30": "LABEL_30",
76
+ "31": "LABEL_31",
77
+ "32": "LABEL_32",
78
+ "33": "LABEL_33",
79
+ "34": "LABEL_34",
80
+ "35": "LABEL_35",
81
+ "36": "LABEL_36",
82
+ "37": "LABEL_37",
83
+ "38": "LABEL_38",
84
+ "39": "LABEL_39",
85
+ "40": "LABEL_40",
86
+ "41": "LABEL_41",
87
+ "42": "LABEL_42",
88
+ "43": "LABEL_43",
89
+ "44": "LABEL_44",
90
+ "45": "LABEL_45",
91
+ "46": "LABEL_46",
92
+ "47": "LABEL_47"
93
+ },
94
+ "label2id": {
95
+ "LABEL_0": 0,
96
+ "LABEL_1": 1,
97
+ "LABEL_2": 2,
98
+ "LABEL_3": 3,
99
+ "LABEL_4": 4,
100
+ "LABEL_5": 5,
101
+ "LABEL_6": 6,
102
+ "LABEL_7": 7,
103
+ "LABEL_8": 8,
104
+ "LABEL_9": 9,
105
+ "LABEL_10": 10,
106
+ "LABEL_11": 11,
107
+ "LABEL_12": 12,
108
+ "LABEL_13": 13,
109
+ "LABEL_14": 14,
110
+ "LABEL_15": 15,
111
+ "LABEL_16": 16,
112
+ "LABEL_17": 17,
113
+ "LABEL_18": 18,
114
+ "LABEL_19": 19,
115
+ "LABEL_20": 20,
116
+ "LABEL_21": 21,
117
+ "LABEL_22": 22,
118
+ "LABEL_23": 23,
119
+ "LABEL_24": 24,
120
+ "LABEL_25": 25,
121
+ "LABEL_26": 26,
122
+ "LABEL_27": 27,
123
+ "LABEL_28": 28,
124
+ "LABEL_29": 29,
125
+ "LABEL_30": 30,
126
+ "LABEL_31": 31,
127
+ "LABEL_32": 32,
128
+ "LABEL_33": 33,
129
+ "LABEL_34": 34,
130
+ "LABEL_35": 35,
131
+ "LABEL_36": 36,
132
+ "LABEL_37": 37,
133
+ "LABEL_38": 38,
134
+ "LABEL_39": 39,
135
+ "LABEL_40": 40,
136
+ "LABEL_41": 41,
137
+ "LABEL_42": 42,
138
+ "LABEL_43": 43,
139
+ "LABEL_44": 44,
140
+ "LABEL_45": 45,
141
+ "LABEL_46": 46,
142
+ "LABEL_47": 47
143
+ },
144
+ "tokenizer_class": null,
145
+ "prefix": null,
146
+ "bos_token_id": null,
147
+ "pad_token_id": 0,
148
+ "eos_token_id": null,
149
+ "sep_token_id": null,
150
+ "decoder_start_token_id": null,
151
+ "task_specific_params": null,
152
+ "problem_type": null,
153
+ "_name_or_path": "",
154
+ "transformers_version": "4.44.2",
155
+ "vocab_size": 62720,
156
+ "d_model": 512,
157
+ "n_layers": 12,
158
+ "n_heads": 8,
159
+ "expansion_ratio": 4,
160
+ "dropout": 0.0,
161
+ "activation": "gelu",
162
+ "norm_eps": 1e-05,
163
+ "num_bins": 51,
164
+ "max_seq_length": 1024,
165
+ "cell_emb_style": "cls",
166
+ "classifier_dropout": 0.1,
167
+ "model_type": "tahoe_x1"
168
+ }
gene_order.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e9ec9c62496e85e4e7e36e6ef6f20f3f140ec08575b47d8122696d27b49087
3
+ size 442736
label_map.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": "B",
3
+ "1": "CD1c-positive",
4
+ "2": "CD4-positive,",
5
+ "3": "CD8-positive,",
6
+ "4": "T",
7
+ "5": "acinar",
8
+ "6": "alveolar",
9
+ "7": "alveolar",
10
+ "8": "bronchial",
11
+ "9": "bronchus",
12
+ "10": "brush",
13
+ "11": "capillary",
14
+ "12": "classical",
15
+ "13": "club",
16
+ "14": "conventional",
17
+ "15": "dendritic",
18
+ "16": "endothelial",
19
+ "17": "epithelial",
20
+ "18": "fibroblast",
21
+ "19": "hematopoietic",
22
+ "20": "ionocyte",
23
+ "21": "lung",
24
+ "22": "mast",
25
+ "23": "mesothelial",
26
+ "24": "mucus",
27
+ "25": "multiciliated",
28
+ "26": "multiciliated",
29
+ "27": "myofibroblast",
30
+ "28": "nasal",
31
+ "29": "natural",
32
+ "30": "non-classical",
33
+ "31": "plasma",
34
+ "32": "plasmacytoid",
35
+ "33": "pulmonary",
36
+ "34": "pulmonary",
37
+ "35": "pulmonary",
38
+ "36": "pulmonary",
39
+ "37": "pulmonary",
40
+ "38": "respiratory",
41
+ "39": "respiratory",
42
+ "40": "serous",
43
+ "41": "smooth",
44
+ "42": "stromal",
45
+ "43": "tracheobronchial",
46
+ "44": "tracheobronchial",
47
+ "45": "tracheobronchial",
48
+ "46": "unknown",
49
+ "47": "vein"
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ed6cd81baeba6d94694d6ae1598baa23d65d9b5df4e04f482d6cecd13ef236
3
+ size 280953952
vocab.json ADDED
The diff for this file is too large to render. See raw diff