miguelcsx commited on
Commit
e771fea
·
verified ·
1 Parent(s): 78a9612

Upload folder using huggingface_hub

Browse files
manifest.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "corpus_null_audit": {
3
+ "brown": {
4
+ "pairs": 11125,
5
+ "retained_by_prefix": [
6
+ 0,
7
+ 0,
8
+ 0
9
+ ],
10
+ "retained_fraction_by_prefix": [
11
+ 0.0,
12
+ 0.0,
13
+ 0.0
14
+ ]
15
+ },
16
+ "ppmi": {
17
+ "pairs": 11125,
18
+ "retained_direct": 0,
19
+ "retained_two_hop": 0
20
+ }
21
+ },
22
+ "document_disjoint": true,
23
+ "files": {
24
+ "special_tokens_map.json": "2be97b602cd0e4a6c2874cbf03c0d1025b3af5474666da931bc04f6c23a9a39d",
25
+ "tokenizer.json": "2b8d1b3f51c0d8f276a64ea6a69efa50b4d9899780f1b282b4d0dcb7be5bbb0f",
26
+ "tokenizer_config.json": "8f4a998564d87fc85b27652f0b295677a1e03744bf400bfacc342b700cc3653a",
27
+ "word_start_mask.npy": "80ca7ca13174695ac5f3b287377c52711103a9d2839c019ed5d45c110cee8880"
28
+ },
29
+ "microdocuments": {
30
+ "null_assignment": "deterministic-repaired-permutation",
31
+ "occurrence_cap_per_anchor": 256,
32
+ "pair_words": 10,
33
+ "scheduler": "round-robin-drop-exhausted"
34
+ },
35
+ "partition_proof": {
36
+ "holdout": {
37
+ "document_ids_sha256": "3f1565055bcf177a3d721f27b980409e2e88093f9b94db4451e5ec2a89a8012f",
38
+ "documents": 9282,
39
+ "text_sha256": "6659bdddb99e32a57b55a76fdd5841a4c3242040b1b54db63efaf3e560a9c169",
40
+ "words": 100000
41
+ },
42
+ "inducer": {
43
+ "document_ids_sha256": "1ef8aeecb319086b66c3da8c9a84c1856067c3bd4248300e71e6ca52d175295c",
44
+ "documents": 93866,
45
+ "text_sha256": "a3555fec3a53982285698c9c5902292006196226b7c5dff5f1c0be524358a160",
46
+ "words": 1000000
47
+ },
48
+ "lm": {
49
+ "document_ids_sha256": "38053791854cf2802344d873437b646824fa7ef1c52b23f4b70fdfd571d2eaf3",
50
+ "documents": 835041,
51
+ "text_sha256": "4c2dc3f0f93e3cbc2025e398e25468686f30d7a39c79aa95491d41d978926787",
52
+ "words": 8900000
53
+ }
54
+ },
55
+ "partitions": {
56
+ "holdout": 100000,
57
+ "inducer": 1000000,
58
+ "lm": 8900000
59
+ },
60
+ "prior_audit": {
61
+ "brown_top_5k_coverage": 1.0,
62
+ "matched_null": {
63
+ "degree_exact": true,
64
+ "null_edge_overlap": 0.7830319888734353,
65
+ "null_swaps": 6801,
66
+ "strength_exact": true
67
+ },
68
+ "ppmi": {
69
+ "mean_degree": 0.719,
70
+ "stability_threshold": 0.8,
71
+ "stable_edges": 719
72
+ },
73
+ "ppmi_top_2k_anchor_coverage": 0.411
74
+ },
75
+ "probe": {
76
+ "items": 20000,
77
+ "match_rate": 1.0,
78
+ "matches": 20000
79
+ },
80
+ "provenance": {
81
+ "brown_binary_sha256": "44851b50c73851a05e2bb7808f1491d7050e37e0e9745e5cbf0f9ebc9b20b3fd",
82
+ "brown_commit": "fe90f87f9cd10d76c834166b4a8560eae3bc38c9",
83
+ "builder_sha256": "621a511ad680f6e40b676eb41eb6a9493412b3d5bd8d07c036a0830997256b69",
84
+ "graph_builder_sha256": "d5c9891df65fb37c43f3a8b5edf6672be4f382f9963a3ab9c13583f588c0eec2",
85
+ "source_data_sha256": "3a4ada4f0c6526d4e678a0bc0d5651e86ee06b9c1245046dcb02ebdf295bf654"
86
+ },
87
+ "relational_words": {
88
+ "brown": 111250,
89
+ "ppmi": 111250
90
+ },
91
+ "schema_version": 2,
92
+ "source_repo": "miguelcsx/babylm-orderlab-causal-affordance-v1",
93
+ "source_revision": "40fda5368a4b1179020d80c1a3ebdc0a40c70dd5",
94
+ "training_words": 8900000
95
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "model_max_length": 512,
6
+ "pad_token": "<pad>",
7
+ "tokenizer_class": "PreTrainedTokenizerFast",
8
+ "unk_token": "<unk>"
9
+ }
word_start_mask.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ca7ca13174695ac5f3b287377c52711103a9d2839c019ed5d45c110cee8880
3
+ size 16512