Saiful Haq
commited on
Commit
•
3780c15
1
Parent(s):
520e5d2
Added language: ben_Beng
Browse files- ben_Beng-nllb1.3b-moses/colbert-50000/artifact.metadata +57 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/config.json +31 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/pytorch_model.bin +3 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/special_tokens_map.json +7 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/tokenizer.json +0 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/tokenizer_config.json +13 -0
- ben_Beng-nllb1.3b-moses/colbert-50000/vocab.txt +0 -0
ben_Beng-nllb1.3b-moses/colbert-50000/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 |
+
"index_path": null,
|
10 |
+
"nbits": 1,
|
11 |
+
"kmeans_niters": 4,
|
12 |
+
"resume": false,
|
13 |
+
"similarity": "cosine",
|
14 |
+
"bsize": 128,
|
15 |
+
"accumsteps": 1,
|
16 |
+
"lr": 3e-6,
|
17 |
+
"maxsteps": 500000,
|
18 |
+
"save_every": null,
|
19 |
+
"warmup": null,
|
20 |
+
"warmup_bert": null,
|
21 |
+
"relu": false,
|
22 |
+
"nway": 2,
|
23 |
+
"use_ib_negatives": false,
|
24 |
+
"reranker": false,
|
25 |
+
"distillation_alpha": 1.0,
|
26 |
+
"ignore_scores": false,
|
27 |
+
"model_name": null,
|
28 |
+
"query_maxlen": 32,
|
29 |
+
"attend_to_mask_tokens": false,
|
30 |
+
"interaction": "colbert",
|
31 |
+
"dim": 128,
|
32 |
+
"doc_maxlen": 220,
|
33 |
+
"mask_punctuation": true,
|
34 |
+
"checkpoint": "bert-base-multilingual-uncased",
|
35 |
+
"triples": "data\/\/triples.train.tsv",
|
36 |
+
"collection": "..\/data_nllb_1.3B_quantized_8bit\/256\/ben_Beng\/\/collection.tsv",
|
37 |
+
"queries": "..\/data_nllb_1.3B_quantized_8bit\/256\/ben_Beng\/query.train.tsv",
|
38 |
+
"index_name": null,
|
39 |
+
"overwrite": false,
|
40 |
+
"root": "\/saif\/saif_ir\/indicIRsuite\/ColBERT\/experiments",
|
41 |
+
"experiment": "mmarco_moses_nllb_1.3B",
|
42 |
+
"index_root": null,
|
43 |
+
"name": "2023-10\/02\/08.45.06",
|
44 |
+
"rank": 0,
|
45 |
+
"nranks": 1,
|
46 |
+
"amp": true,
|
47 |
+
"gpus": 1,
|
48 |
+
"meta": {
|
49 |
+
"hostname": "ddbf18d969d5",
|
50 |
+
"git_branch": "main",
|
51 |
+
"git_hash": "43ae55077c5c793d382b7ee3ed6b57630bbcd22e",
|
52 |
+
"git_commit_datetime": "2023-04-19 17:21:22-07:00",
|
53 |
+
"current_datetime": "Oct 02, 2023 ; 5:35PM UTC (+0000)",
|
54 |
+
"cmd": "train_multilingual-final.py ben_Beng nllb_1.3B",
|
55 |
+
"version": "colbert-v0.4"
|
56 |
+
}
|
57 |
+
}
|
ben_Beng-nllb1.3b-moses/colbert-50000/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"HF_ColBERT"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.28.1",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 105879
|
31 |
+
}
|
ben_Beng-nllb1.3b-moses/colbert-50000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e136dea66244da22e6e0ab1b46f8488b22630eb9181deed409847f16637ed67e
|
3 |
+
size 669891377
|
ben_Beng-nllb1.3b-moses/colbert-50000/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 |
+
}
|
ben_Beng-nllb1.3b-moses/colbert-50000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ben_Beng-nllb1.3b-moses/colbert-50000/tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
ben_Beng-nllb1.3b-moses/colbert-50000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|