Eli Browne commited on
Commit
3c6447c
1 Parent(s): 0512d23

Initial commit: mixed up models, THIS is plain ColBERT; other model is LegalBERT; names are updated to reflect this

Browse files
artifact.metadata ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 20,
14
+ "resume": false,
15
+ "similarity": "cosine",
16
+ "bsize": 32,
17
+ "accumsteps": 1,
18
+ "lr": 5e-6,
19
+ "maxsteps": 500000,
20
+ "save_every": 73,
21
+ "warmup": 73,
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": "baseColBERT",
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": "colbert-ir\/colbertv2.0",
37
+ "triples": ".\/data\/triples.train.colbert.jsonl",
38
+ "collection": ".\/data\/corpus.train.colbert.tsv",
39
+ "queries": ".\/data\/queries.train.colbert.tsv",
40
+ "index_name": null,
41
+ "overwrite": false,
42
+ "root": ".ragatouille\/",
43
+ "experiment": "colbert",
44
+ "index_root": null,
45
+ "name": "2024-07\/17\/13.39.56",
46
+ "rank": 0,
47
+ "nranks": 1,
48
+ "amp": true,
49
+ "gpus": 1,
50
+ "avoid_fork_if_possible": false,
51
+ "meta": {
52
+ "hostname": "jagupard28.stanford.edu",
53
+ "git_branch": "main",
54
+ "git_hash": "4e1a837629bb109bf7e4b6dc2650dced9c0b9bff",
55
+ "git_commit_datetime": "2024-07-17 12:04:00-07:00",
56
+ "current_datetime": "Jul 17, 2024 ; 1:44PM PDT (-0700)",
57
+ "cmd": "fine_tune.py",
58
+ "version": "colbert-v0.4"
59
+ }
60
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "colbert-ir/colbertv2.0",
3
+ "architectures": [
4
+ "HF_ColBERT"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
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
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.42.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0763cff4ecdd9e727baec52a9bb15cc64f3fe066fd0ae7da38eb86cad5ee5a25
3
+ size 438345624
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff