nickosn commited on
Commit
72c93f5
·
verified ·
1 Parent(s): d74b1ca

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. basic_math_mj/part-00-00000.npy +3 -0
  2. basic_math_mj/part-01-00000.npy +3 -0
  3. basic_math_mj/part-02-00000.npy +3 -0
  4. basic_math_mj/part-03-00000.npy +3 -0
  5. basic_math_mj/part-04-00000.npy +3 -0
  6. basic_math_mj/part-05-00000.npy +3 -0
  7. basic_math_mj/part-06-00000.npy +3 -0
  8. basic_math_mj/part-07-00000.npy +3 -0
  9. basic_math_mj/part-08-00000.npy +3 -0
  10. basic_math_mj/part-12-00000.npy +3 -0
  11. basic_math_mj/part-13-00000.npy +3 -0
  12. basic_math_mj/part-17-00000.npy +3 -0
  13. basic_math_mj/part-2-00000.npy +3 -0
  14. basic_math_mj/part-20-00000.npy +3 -0
  15. basic_math_mj/part-21-00000.npy +3 -0
  16. basic_math_mj/part-22-00000.npy +3 -0
  17. basic_math_mj/part-23-00000.npy +3 -0
  18. basic_math_mj/part-24-00000.npy +3 -0
  19. basic_math_mj/part-25-00000.npy +3 -0
  20. basic_math_mj/part-26-00000.npy +3 -0
  21. basic_math_mj/part-27-00000.npy +3 -0
  22. basic_math_mj/part-28-00000.npy +3 -0
  23. basic_math_mj/part-29-00000.npy +3 -0
  24. basic_math_mj/part-3-00000.npy +3 -0
  25. basic_math_mj/part-30-00000.npy +3 -0
  26. basic_math_mj/part-31-00000.npy +3 -0
  27. basic_math_mj/part-32-00000.npy +3 -0
  28. basic_math_mj/part-33-00000.npy +3 -0
  29. basic_math_mj/part-34-00000.npy +3 -0
  30. basic_math_mj/part-4-00000.npy +3 -0
  31. basic_math_mj/part-5-00000.npy +3 -0
  32. dclm/part-2-00000.npy +3 -0
  33. download.sh +65 -0
  34. mathcoder2-synthmath/part-00-00000.npy +3 -0
  35. mathcoder2-synthmath/part-01-00000.npy +3 -0
  36. mathcoder2-synthmath/part-02-00000.npy +3 -0
  37. mathcoder2-synthmath/part-03-00000.npy +3 -0
  38. mathcoder2-synthmath/part-04-00000.npy +3 -0
  39. mathcoder2-synthmath/part-05-00000.npy +3 -0
  40. mathcoder2-synthmath/part-06-00000.npy +3 -0
  41. mathcoder2-synthmath/part-07-00000.npy +3 -0
  42. mathcoder2-synthmath/part-08-00000.npy +3 -0
  43. mathcoder2-synthmath/part-09-00000.npy +3 -0
  44. mathcoder2-synthmath/part-10-00000.npy +3 -0
  45. mathcoder2-synthmath/part-11-00000.npy +3 -0
  46. mathcoder2-synthmath/part-12-00000.npy +3 -0
  47. mathcoder2-synthmath/part-13-00000.npy +3 -0
  48. mathcoder2-synthmath/part-14-00000.npy +3 -0
  49. mathcoder2-synthmath/part-15-00000.npy +3 -0
  50. mathcoder2-synthmath/part-16-00000.npy +3 -0
basic_math_mj/part-00-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb12a1a24233ecca23964732627d0d7719dcca9079a45beee39e298992941ab9
3
+ size 396000
basic_math_mj/part-01-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398da4f497a6ea407f4a12e7b165d4bdabf8a64f62ab8f85c07a7b81888f64ec
3
+ size 760000
basic_math_mj/part-02-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48a73961a7917c7540d5c228fe2af9eab6ff8ee6ed606e08ce342c9b7e42018
3
+ size 910800
basic_math_mj/part-03-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898805438afed6d5f9e38a52bbdd0d1afdca49cff4d79c4f3f3479bc8edeab88
3
+ size 3524400
basic_math_mj/part-04-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d842d5c7bb00d2f09c2668f7c8b773bc38442b8ab76745b523f2ac9198ca59d8
3
+ size 3400000
basic_math_mj/part-05-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b61262ec144af65bc193e955c6f116f73e3746681e799c58783c6efbce1f57
3
+ size 48048
basic_math_mj/part-06-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9373a5436b942086bd1651d7797626d58935d40a50001f08d513266dca47bcf2
3
+ size 77792
basic_math_mj/part-07-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed70ee92a43f8daf9d5fc6cafd4e0aca5f7ab7b5534b8b6b25ce99b00a5c96e
3
+ size 435600
basic_math_mj/part-08-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d506f9bbfaf9ac3f76b07e6266c37882ec6f6066cb7d5d571dcbeb0d45ae3c
3
+ size 320000
basic_math_mj/part-12-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613f2a71e840f6224daaa35511c8c9a612f3986b6ee6ee71ff693702904a36cf
3
+ size 396000
basic_math_mj/part-13-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bb6a0589faaf9b6591e5ee988041187129e3aa866e032ff37515a53ac1658e
3
+ size 18304
basic_math_mj/part-17-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e01c772c71a448b275469ce969ac2a66e176505b346768705f2df0ceaea76fa
3
+ size 752400
basic_math_mj/part-2-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aab445c68288b2d5d39e1feb7085ff60d6f7a299a9eab8577522e5b20a2be18
3
+ size 534936
basic_math_mj/part-20-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03cb432710648e76158dc9d3409ef9df8575472d061164dd6dbe67cb1177a388
3
+ size 1360000
basic_math_mj/part-21-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12447aa209babe103718605600f33404a39b1982f7edc8927743c9e1ff8e4c1e
3
+ size 435600
basic_math_mj/part-22-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf79ee0ce91534345a3d8573dd02c1f55f549361af4c9165252cbce5a45def0
3
+ size 760000
basic_math_mj/part-23-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fccd92ec1544c538f06197e344b6f86e660dac08ed55d6bfb1262e763a288f1
3
+ size 746440
basic_math_mj/part-24-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604392424d9265fa1bc20816390bbc9559dd7fa16a12a28d547a1bbf57b488ae
3
+ size 346440
basic_math_mj/part-25-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d848e114a62c85fcf699a2186ff7ffe6a42b384c11f5d77ea2d8a567b39b1ed
3
+ size 1386000
basic_math_mj/part-26-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30f031d4eb0dcaaca245165dae595321fe9b4adb9802d367db606f80eb5ff61
3
+ size 194480
basic_math_mj/part-27-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50691ca6b081352fef3b286f20000a83f2012a0dae19c6919bd6ec4732e12b9a
3
+ size 752400
basic_math_mj/part-28-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1563d50e8fb4f0c6b5d8e407b2379de541bfa142736036087f1fcac68a0c916a
3
+ size 720000
basic_math_mj/part-29-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b56b654c1256470e61d33ce38024f860c3a0abe97d5669b8dc39dc45f6531ae
3
+ size 320000
basic_math_mj/part-3-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbce85344bc01085ce34bf87828d71a914cdd8ee4e527c1ac66b5062a4e98095
3
+ size 605308
basic_math_mj/part-30-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fa39241db16699c98e800b66d76c0837b9fe4012889b204f216fe288e41175
3
+ size 1386440
basic_math_mj/part-31-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7da2180717d405b74401d3d23558b8f372b37d107739332dec004725f6178cf
3
+ size 3505780
basic_math_mj/part-32-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddeb3f186ebf93635ab570d9ba9b7da1593e18793b6c9450144245e87cf79d02
3
+ size 720000
basic_math_mj/part-33-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db07defda375f7a314aff04b89d974b3c85782205bb3f78713ddb849d7f5ce8f
3
+ size 3400000
basic_math_mj/part-34-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54d25e1c39c1fbe646aff841759db289f87dbe4b93097e95a58ab12459a5d41
3
+ size 346440
basic_math_mj/part-4-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9701ca6e0e50ec634ee07e86af842920f1f30f73a83e933d36f8a5075d7beae3
3
+ size 1640092
basic_math_mj/part-5-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ffeb5ada90594021464fcdce2716a0ce42376613fcdc7deca95527108d9172e
3
+ size 3589284
dclm/part-2-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290fe9d3bf15a98ce8030e5f3f07dd07b863aa4985fd601a51a38aacece8b2ae
3
+ size 35583812
download.sh ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/bin/bash
2
+
3
+ # 输入文件路径(包含 URL 的文件)
4
+ input_file="urls.txt"
5
+
6
+ # 最大并发数(可以根据需要调整)
7
+ max_concurrent=15
8
+
9
+ # 检查输入文件是否存在
10
+ if [[ ! -f "$input_file" ]]; then
11
+ echo "错误:文件 $input_file 不存在!"
12
+ exit 1
13
+ fi
14
+
15
+ # 计数器,用于跟踪当前正在运行的任务数量
16
+ running_tasks=0
17
+
18
+ # 逐行读取文件中的 URL
19
+ while IFS= read -r url; do
20
+ # 检查 URL 是否为空
21
+ if [[ -z "$url" ]]; then
22
+ continue
23
+ fi
24
+
25
+ # 提取 preprocessed 后面的字段作为目录名
26
+ directory=$(echo "$url" | grep -oP '(?<=preprocessed/)[^/]+')
27
+
28
+ # 如果提取不到目录名,跳过该 URL
29
+ if [[ -z "$directory" ]]; then
30
+ echo "警告:URL $url 缺少有效的目录信息,跳过!"
31
+ continue
32
+ fi
33
+
34
+ # 创建目标目录(如果不存在)
35
+ mkdir -p "$directory"
36
+
37
+ # 提取文件名
38
+ filename=$(basename "$url")
39
+
40
+ # 下载文件到目标目录(并发执行)
41
+ (
42
+ echo "正在下载 $url 到 $directory/$filename ..."
43
+ wget -q -O "$directory/$filename" "$url"
44
+ if [[ $? -eq 0 ]]; then
45
+ echo "下载成功:$directory/$filename"
46
+ else
47
+ echo "下载失败:$url"
48
+ fi
49
+ ) &
50
+
51
+ # 更新并发任务计数器
52
+ running_tasks=$((running_tasks + 1))
53
+
54
+ # 如果达到最大并发数,等待部分任务完成
55
+ if [[ $running_tasks -ge $max_concurrent ]]; then
56
+ wait -n # 等待任意一个后台任务完成
57
+ running_tasks=$((running_tasks - 1))
58
+ fi
59
+
60
+ done < "$input_file"
61
+
62
+ # 等待所有剩余的任务完成
63
+ wait
64
+
65
+ echo "所有文件处理完成!"
mathcoder2-synthmath/part-00-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d5f9ca2382d57ea568366b0239c6dc6974561241f37aef8391fb0fca1e88ab
3
+ size 128877412
mathcoder2-synthmath/part-01-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d03a08107ac028f3390da5b18fb5b3dffe76233c870e9a80c81cbe6652bfdd6
3
+ size 108442852
mathcoder2-synthmath/part-02-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed2b4374e76e08ad1d1b6315d7b4ec078c324ad9b690e470f745772dbe53a43
3
+ size 116948080
mathcoder2-synthmath/part-03-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c399da3f1db9f38b1333e6a7f671ea2c7f21477de797deae594e47cadf1ec12
3
+ size 100188860
mathcoder2-synthmath/part-04-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5427e06cf74581aada0e497a9d44d5b77f510c1803dfd3b4814d150f0d8efc5
3
+ size 151711548
mathcoder2-synthmath/part-05-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3aaa01f05b985b665003de8a7ac5efeb56dd2ea9d7eb2f26040f7db84a0963c
3
+ size 517088260
mathcoder2-synthmath/part-06-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc31b1cbd0d9ffd01393612208b6ba6fe28dc7b25cdf1e993ca12a4991128c3d
3
+ size 139817528
mathcoder2-synthmath/part-07-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408d7ef57f954067e84c339a83e5e0786bc77555f80f3f9bf452d8eff0beea82
3
+ size 108618344
mathcoder2-synthmath/part-08-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62530bc95bb46590b04bc6b03a7303cf1ec6353fa84bb1d4f9f1f34f86b0bc7
3
+ size 518112528
mathcoder2-synthmath/part-09-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ebbafa606fdc8f3da787dd9e8c306856a2901a4efbff9f53fa5498c0b884e7
3
+ size 133336460
mathcoder2-synthmath/part-10-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2006f18a0a719755ea25465c8c0d1824b2569a89447296d6a581b7749227057e
3
+ size 109192520
mathcoder2-synthmath/part-11-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6bc563fe8f40b195f14cab0b3af0a4e4cdb577cfac4e1c592d8a2b25a0967d
3
+ size 151643232
mathcoder2-synthmath/part-12-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466f4ce4a15cd7e4266ff2475f9977c2edff8f1f13b74b2e5f84ff580ecf080a
3
+ size 127514692
mathcoder2-synthmath/part-13-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c05e1c15f898e89b917efec3d4a24c03cb2062f0202afaa7c7622a63aefe79b
3
+ size 152834308
mathcoder2-synthmath/part-14-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3168772336a2a63298b4fa333de1f3bb329d12e04889be42d5a8c1564a24335a
3
+ size 197948716
mathcoder2-synthmath/part-15-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c985a20fd187b5f4bd70bafc77a4314f0ecca1616d39c177d2f0cba6156c54bd
3
+ size 163433248
mathcoder2-synthmath/part-16-00000.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246830d89901d0347e912515fdafd8dc88118c45bddf2a8ee25736734a4d7552
3
+ size 130902512