Commit
•
c2cf850
1
Parent(s):
a6a2a36
push model
Browse files- .gitattributes +1 -0
- artifact.metadata +58 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
artifact.metadata
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "l2",
|
14 |
+
"bsize": 64,
|
15 |
+
"accumsteps": 1,
|
16 |
+
"lr": 5e-6,
|
17 |
+
"maxsteps": 400000,
|
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": "xlm-roberta-large",
|
28 |
+
"force_resize_embeddings": true,
|
29 |
+
"query_maxlen": 32,
|
30 |
+
"attend_to_mask_tokens": false,
|
31 |
+
"interaction": "colbert",
|
32 |
+
"dim": 128,
|
33 |
+
"doc_maxlen": 180,
|
34 |
+
"mask_punctuation": true,
|
35 |
+
"checkpoint": "\/exp\/eyang\/data\/checkpoints\/colbert_xlm-roberta-large\/train.py\/hc4langs-5e-6\/checkpoints\/colbert.dnn",
|
36 |
+
"triples": "\/expscratch\/eyang\/workspace\/clir-pretrain\/multilingual\/mixed_msmarco\/hc4_combined.tsv",
|
37 |
+
"collection": null,
|
38 |
+
"queries": null,
|
39 |
+
"index_name": null,
|
40 |
+
"overwrite": false,
|
41 |
+
"root": "\/expscratch\/eyang\/checkpoints",
|
42 |
+
"experiment": "colbert_xlm-roberta-large",
|
43 |
+
"index_root": null,
|
44 |
+
"name": "2023-07\/03\/21.04.26",
|
45 |
+
"rank": 0,
|
46 |
+
"nranks": 1,
|
47 |
+
"amp": true,
|
48 |
+
"gpus": 0,
|
49 |
+
"meta": {
|
50 |
+
"hostname": "test1",
|
51 |
+
"git_branch": "plaid-x",
|
52 |
+
"git_hash": "c9eb35b2b1e073b1e4c296587bc952c61fb11d9b",
|
53 |
+
"git_commit_datetime": "2023-07-03 20:22:10-04:00",
|
54 |
+
"current_datetime": "Jul 03, 2023 ; 9:36PM EDT (-0400)",
|
55 |
+
"cmd": "\/home\/hltcoe\/eyang\/.conda\/envs\/interactive-new\/bin\/ipython --profile=eugene",
|
56 |
+
"version": "colbert-v0.4"
|
57 |
+
}
|
58 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"HF_ColBERT"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.25.1",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250004
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:375b4436bfe51917e409ae5ce6623b7241d344ac121272ba36d655537dae0389
|
3 |
+
size 2240228465
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c19ec03247ee31e5f42772ac32bde8dca2727b30c8310c2e585df4980a8db230
|
3 |
+
size 17083032
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-large",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|