akpsahan commited on
Commit
5f448f1
·
verified ·
1 Parent(s): a948426

Manifest — 4.0B tokens

Browse files
Files changed (1) hide show
  1. data/manifest.json +9 -39
data/manifest.json CHANGED
@@ -1,51 +1,21 @@
1
  {
2
- "total_tokens": 23121221911,
3
- "total_bytes": 46242443822,
4
  "format": "uint16",
5
  "tokenizer": "akpsahan/s8",
6
  "vocab_size": 3200,
7
  "datasets": {
8
- "english_cx": {
9
- "repo": "akpsahan/EnglishCX",
10
- "tokens": 8000000000,
11
- "budget": 8000000000,
12
- "coverage": 100.0
13
- },
14
- "fineweb_edu": {
15
- "repo": "HuggingFaceFW/fineweb-edu",
16
- "tokens": 5000000000,
17
- "budget": 5000000000,
18
- "coverage": 100.0
19
- },
20
- "nemotron_math": {
21
- "repo": "nvidia/Nemotron-CC-Math-v1",
22
- "tokens": 0,
23
  "budget": 4000000000,
24
- "coverage": 0.0
25
- },
26
- "sinhala_cx": {
27
- "repo": "akpsahan/SinhalaCX",
28
- "tokens": 8000000000,
29
- "budget": 8000000000,
30
  "coverage": 100.0
31
  },
32
- "sinhalen_gz": {
33
- "repo": "akpsahan/SinhalenGZ",
34
- "tokens": 2000000000,
35
- "budget": 2000000000,
36
  "coverage": 100.0
37
- },
38
- "coder_combined": {
39
- "repo": "akpsahan/Coder-combined-pretraining-corpus",
40
- "tokens": 74567978,
41
- "budget": 2500000000,
42
- "coverage": 3.0
43
- },
44
- "langchain_docs": {
45
- "repo": "Deepak9/langchain-docs",
46
- "tokens": 46653933,
47
- "budget": 500000000,
48
- "coverage": 9.3
49
  }
50
  }
51
  }
 
1
  {
2
+ "total_tokens": 4000008192,
3
+ "total_bytes": 8000016384,
4
  "format": "uint16",
5
  "tokenizer": "akpsahan/s8",
6
  "vocab_size": 3200,
7
  "datasets": {
8
+ "math": {
9
+ "repo": "open-web-math/open-web-math",
10
+ "tokens": 4000000000,
 
 
 
 
 
 
 
 
 
 
 
 
11
  "budget": 4000000000,
 
 
 
 
 
 
12
  "coverage": 100.0
13
  },
14
+ "ot": {
15
+ "repo": "akpsahan/ot",
16
+ "tokens": 8192,
17
+ "budget": 8192,
18
  "coverage": 100.0
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  }
21
  }