Sentence Similarity
Safetensors
Japanese
RAGatouille
bert
ColBERT
bclavie commited on
Commit
e4bedb5
1 Parent(s): 5a5fa15

Upload folder using huggingface_hub

Browse files
artifact.metadata ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "query_token_id": "[unused0]",
3
+ "doc_token_id": "[unused1]",
4
+ "query_token": "[\u8cea\u554fs]",
5
+ "doc_token": "[\u6587\u66f8]",
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": 4,
17
+ "accumsteps": 1,
18
+ "lr": 1e-5,
19
+ "maxsteps": 500000,
20
+ "save_every": null,
21
+ "warmup": 10000,
22
+ "warmup_bert": null,
23
+ "relu": false,
24
+ "nway": 32,
25
+ "use_ib_negatives": true,
26
+ "reranker": false,
27
+ "distillation_alpha": 1.0,
28
+ "ignore_scores": false,
29
+ "model_name": "ja_colbert",
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": "bclavie\/JaColBERT",
37
+ "triples": ".\/\/triplets.jsonl",
38
+ "collection": ".\/\/collection.tsv",
39
+ "queries": ".\/\/queries.tsv",
40
+ "index_name": null,
41
+ "overwrite": false,
42
+ "root": "\/admin\/home-bclavie\/mcolbert\/jacolbertv2\/experiments",
43
+ "experiment": "default",
44
+ "index_root": null,
45
+ "name": "2024-03\/01\/15.03.55",
46
+ "rank": 0,
47
+ "nranks": 8,
48
+ "amp": true,
49
+ "gpus": 8,
50
+ "avoid_fork_if_possible": false,
51
+ "meta": {
52
+ "hostname": "ip-10-0-200-106",
53
+ "current_datetime": "Mar 02, 2024 ; 5:10PM UTC (+0000)",
54
+ "cmd": "train.py",
55
+ "version": "colbert-v0.4"
56
+ }
57
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bclavie/JaColBERT",
3
+ "architectures": [
4
+ "HF_ColBERT"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.38.2",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32768
25
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d91bbcc5120c42852b058a87242d62a2213c3f7620ff7265bb9f4602db210d0
3
+ size 445245352
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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": false,
47
+ "do_subword_tokenize": true,
48
+ "do_word_tokenize": true,
49
+ "jumanpp_kwargs": null,
50
+ "mask_token": "[MASK]",
51
+ "mecab_kwargs": {
52
+ "mecab_dic": "unidic_lite"
53
+ },
54
+ "model_max_length": 512,
55
+ "never_split": null,
56
+ "pad_token": "[PAD]",
57
+ "sep_token": "[SEP]",
58
+ "subword_tokenizer_type": "wordpiece",
59
+ "sudachi_kwargs": null,
60
+ "tokenizer_class": "BertJapaneseTokenizer",
61
+ "unk_token": "[UNK]",
62
+ "word_tokenizer_type": "mecab"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff