Hugging Face's logo

carlesoctav
/
IndoColbert

Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
carlesoctav commited on
Commit
24027df
·
verified ·
1 Parent(s): 0ca137f

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. artifact.metadata +57 -0
  2. config.json +47 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. vocab.txt +0 -0
artifact.metadata ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "query_token_id": "[unused0]",
3
+ "doc_token_id": "[unused1]",
4
+ "query_token": "[Q]",
5
+ "doc_token": "[D]",
6
+ "ncells": null,
7
+ "centroid_score_threshold": null,
8
+ "ndocs": null,
9
+ "load_index_with_mmap": false,
10
+ "index_path": null,
11
+ "index_bsize": 64,
12
+ "nbits": 2,
13
+ "kmeans_niters": 4,
14
+ "resume": false,
15
+ "similarity": "cosine",
16
+ "bsize": 32,
17
+ "accumsteps": 1,
18
+ "lr": 5e-6,
19
+ "maxsteps": 500000,
20
+ "save_every": 61050,
21
+ "warmup": 61050,
22
+ "warmup_bert": null,
23
+ "relu": false,
24
+ "nway": 2,
25
+ "use_ib_negatives": true,
26
+ "reranker": false,
27
+ "distillation_alpha": 1.0,
28
+ "ignore_scores": false,
29
+ "model_name": "indocolbert",
30
+ "query_maxlen": 32,
31
+ "attend_to_mask_tokens": false,
32
+ "interaction": "colbert",
33
+ "dim": 128,
34
+ "doc_maxlen": 256,
35
+ "mask_punctuation": true,
36
+ "checkpoint": "indobenchmark\/indobert-base-p2",
37
+ "triples": "data\/indotriplet\/triples.train.colbert.jsonl",
38
+ "collection": "data\/indotriplet\/corpus.train.colbert.tsv",
39
+ "queries": "data\/indotriplet\/queries.train.colbert.tsv",
40
+ "index_name": null,
41
+ "overwrite": false,
42
+ "root": ".ragatouille\/",
43
+ "experiment": "colbert",
44
+ "index_root": null,
45
+ "name": "2024-06\/19\/08.44.30",
46
+ "rank": 0,
47
+ "nranks": 1,
48
+ "amp": true,
49
+ "gpus": 1,
50
+ "avoid_fork_if_possible": false,
51
+ "meta": {
52
+ "hostname": "carles",
53
+ "current_datetime": "Jun 20, 2024 ; 2:18AM UTC (+0000)",
54
+ "cmd": "mined_e5_large.py",
55
+ "version": "colbert-v0.4"
56
+ }
57
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indobenchmark/indobert-base-p2",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "HF_ColBERT"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "pooler_fc_size": 768,
37
+ "pooler_num_attention_heads": 12,
38
+ "pooler_num_fc_layers": 3,
39
+ "pooler_size_per_head": 128,
40
+ "pooler_type": "first_token_transform",
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.41.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 50000
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd50c9e0225865d3863004a4e5b955a9f3f947c75224760c162109a6b8a54597
3
+ size 498182056
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff