Hugging Face's logo

tniranjan
/
gptNeo-ta

Safetensors
gpt_neo
Model card Files
xet
Community
tniranjan commited on
Commit
eccc635
·
verified ·
1 Parent(s): 32be578

Training in progress, step 10000

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +2 -6
  2. model.safetensors +2 -2
  3. tokenized_tamil_CulturaX_dataset/dataset_dict.json +1 -0
  4. tokenized_tamil_CulturaX_dataset/train/data-00000-of-00122.arrow +3 -0
  5. tokenized_tamil_CulturaX_dataset/train/data-00001-of-00122.arrow +3 -0
  6. tokenized_tamil_CulturaX_dataset/train/data-00002-of-00122.arrow +3 -0
  7. tokenized_tamil_CulturaX_dataset/train/data-00003-of-00122.arrow +3 -0
  8. tokenized_tamil_CulturaX_dataset/train/data-00004-of-00122.arrow +3 -0
  9. tokenized_tamil_CulturaX_dataset/train/data-00005-of-00122.arrow +3 -0
  10. tokenized_tamil_CulturaX_dataset/train/data-00006-of-00122.arrow +3 -0
  11. tokenized_tamil_CulturaX_dataset/train/data-00007-of-00122.arrow +3 -0
  12. tokenized_tamil_CulturaX_dataset/train/data-00008-of-00122.arrow +3 -0
  13. tokenized_tamil_CulturaX_dataset/train/data-00009-of-00122.arrow +3 -0
  14. tokenized_tamil_CulturaX_dataset/train/data-00010-of-00122.arrow +3 -0
  15. tokenized_tamil_CulturaX_dataset/train/data-00011-of-00122.arrow +3 -0
  16. tokenized_tamil_CulturaX_dataset/train/data-00012-of-00122.arrow +3 -0
  17. tokenized_tamil_CulturaX_dataset/train/data-00013-of-00122.arrow +3 -0
  18. tokenized_tamil_CulturaX_dataset/train/data-00014-of-00122.arrow +3 -0
  19. tokenized_tamil_CulturaX_dataset/train/data-00015-of-00122.arrow +3 -0
  20. tokenized_tamil_CulturaX_dataset/train/data-00016-of-00122.arrow +3 -0
  21. tokenized_tamil_CulturaX_dataset/train/data-00017-of-00122.arrow +3 -0
  22. tokenized_tamil_CulturaX_dataset/train/data-00018-of-00122.arrow +3 -0
  23. tokenized_tamil_CulturaX_dataset/train/data-00019-of-00122.arrow +3 -0
  24. tokenized_tamil_CulturaX_dataset/train/data-00020-of-00122.arrow +3 -0
  25. tokenized_tamil_CulturaX_dataset/train/data-00021-of-00122.arrow +3 -0
  26. tokenized_tamil_CulturaX_dataset/train/data-00022-of-00122.arrow +3 -0
  27. tokenized_tamil_CulturaX_dataset/train/data-00023-of-00122.arrow +3 -0
  28. tokenized_tamil_CulturaX_dataset/train/data-00024-of-00122.arrow +3 -0
  29. tokenized_tamil_CulturaX_dataset/train/data-00025-of-00122.arrow +3 -0
  30. tokenized_tamil_CulturaX_dataset/train/data-00026-of-00122.arrow +3 -0
  31. tokenized_tamil_CulturaX_dataset/train/data-00027-of-00122.arrow +3 -0
  32. tokenized_tamil_CulturaX_dataset/train/data-00028-of-00122.arrow +3 -0
  33. tokenized_tamil_CulturaX_dataset/train/data-00029-of-00122.arrow +3 -0
  34. tokenized_tamil_CulturaX_dataset/train/data-00030-of-00122.arrow +3 -0
  35. tokenized_tamil_CulturaX_dataset/train/data-00031-of-00122.arrow +3 -0
  36. tokenized_tamil_CulturaX_dataset/train/data-00032-of-00122.arrow +3 -0
  37. tokenized_tamil_CulturaX_dataset/train/data-00033-of-00122.arrow +3 -0
  38. tokenized_tamil_CulturaX_dataset/train/data-00034-of-00122.arrow +3 -0
  39. tokenized_tamil_CulturaX_dataset/train/data-00035-of-00122.arrow +3 -0
  40. tokenized_tamil_CulturaX_dataset/train/data-00036-of-00122.arrow +3 -0
  41. tokenized_tamil_CulturaX_dataset/train/data-00037-of-00122.arrow +3 -0
  42. tokenized_tamil_CulturaX_dataset/train/data-00038-of-00122.arrow +3 -0
  43. tokenized_tamil_CulturaX_dataset/train/data-00039-of-00122.arrow +3 -0
  44. tokenized_tamil_CulturaX_dataset/train/data-00040-of-00122.arrow +3 -0
  45. tokenized_tamil_CulturaX_dataset/train/data-00041-of-00122.arrow +3 -0
  46. tokenized_tamil_CulturaX_dataset/train/data-00042-of-00122.arrow +3 -0
  47. tokenized_tamil_CulturaX_dataset/train/data-00043-of-00122.arrow +3 -0
  48. tokenized_tamil_CulturaX_dataset/train/data-00044-of-00122.arrow +3 -0
  49. tokenized_tamil_CulturaX_dataset/train/data-00045-of-00122.arrow +3 -0
  50. tokenized_tamil_CulturaX_dataset/train/data-00046-of-00122.arrow +3 -0
config.json CHANGED
@@ -12,10 +12,6 @@
12
  "global",
13
  "local",
14
  "global",
15
- "local",
16
- "global",
17
- "local",
18
- "global",
19
  "local"
20
  ],
21
  "attention_types": [
@@ -24,7 +20,7 @@
24
  "global",
25
  "local"
26
  ],
27
- 6
28
  ]
29
  ],
30
  "bos_token_id": 50256,
@@ -38,7 +34,7 @@
38
  "max_position_embeddings": 1024,
39
  "model_type": "gpt_neo",
40
  "num_heads": 16,
41
- "num_layers": 12,
42
  "resid_dropout": 0.0,
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.48.3",
 
12
  "global",
13
  "local",
14
  "global",
 
 
 
 
15
  "local"
16
  ],
17
  "attention_types": [
 
20
  "global",
21
  "local"
22
  ],
23
+ 4
24
  ]
25
  ],
26
  "bos_token_id": 50256,
 
34
  "max_position_embeddings": 1024,
35
  "model_type": "gpt_neo",
36
  "num_heads": 16,
37
+ "num_layers": 8,
38
  "resid_dropout": 0.0,
39
  "torch_dtype": "float32",
40
  "transformers_version": "4.48.3",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8747dcbdb0d43a8a6c99dcc0cb3de2025cfb21800401f3db0c9ed419101b2e93
3
- size 813458248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c26b1ae3b666a04072aae648c2eece6ce13e61086dd7349b3f20ab56113241
3
+ size 611962176
tokenized_tamil_CulturaX_dataset/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "validation"]}
tokenized_tamil_CulturaX_dataset/train/data-00000-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09f29d19bd7192254bc3038be0b21cabc45e5cffb1ec3b9ffff761eb9d4f584
3
+ size 497381632
tokenized_tamil_CulturaX_dataset/train/data-00001-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52500425760f186a1966d28a1f9cdd59027db8f500ed9cd97fc6ef7a747c802
3
+ size 493607912
tokenized_tamil_CulturaX_dataset/train/data-00002-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1d777f4eab98a10eea8d72f611f7f7c6c9a6d56fdd0572665d07dcc0378fd6
3
+ size 494228680
tokenized_tamil_CulturaX_dataset/train/data-00003-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e3bd2c78cc9a7dd3133fce457500b6f58b9542a845c06e9b0cd2aba51c647f
3
+ size 502511280
tokenized_tamil_CulturaX_dataset/train/data-00004-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3022cda03909699540c1dfb74771a6a0683697eee4b5be287ff0b4503a1c9713
3
+ size 499485808
tokenized_tamil_CulturaX_dataset/train/data-00005-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85be0815461bdcd0f2120ea915e3315ae481dcc82817ec5ed26a0766abb3505
3
+ size 499387248
tokenized_tamil_CulturaX_dataset/train/data-00006-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d80d9b39d48a6773c82dc210185fb11df584d694b1f606521481a020cec1c0
3
+ size 495876704
tokenized_tamil_CulturaX_dataset/train/data-00007-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efd9ac9aad8212d8f6deb22892f6d1c9543a6cff7d972878871f1505a818020
3
+ size 501272680
tokenized_tamil_CulturaX_dataset/train/data-00008-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797b07fe8e1640f6e571f83e4fd535b0669dda219c7be53716c012c132570981
3
+ size 493478768
tokenized_tamil_CulturaX_dataset/train/data-00009-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8924d14f4b66d34d42f3de68f34c243ceee3d4ecb543da9cc808d5f77c832d9d
3
+ size 501205456
tokenized_tamil_CulturaX_dataset/train/data-00010-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4892390827a065744dcdc3a112b3e150f10078401074274952efcb459345016
3
+ size 496196224
tokenized_tamil_CulturaX_dataset/train/data-00011-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d6bca7a1c716f13010f9937424c10de8447fff48bbd22a536b353a64821d7c
3
+ size 498188272
tokenized_tamil_CulturaX_dataset/train/data-00012-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e80da07ac70a4397c5277bd31a0d6e47c4191b5e0bfbea16149058b1bc2c43b
3
+ size 497566808
tokenized_tamil_CulturaX_dataset/train/data-00013-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12facbfb3fb51d3d1ed2353436b9f34a8fbf61c917ae7517f5b595978c54a4ed
3
+ size 498150920
tokenized_tamil_CulturaX_dataset/train/data-00014-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4fc6c6d570c251c270182fb46354891b220e4e7fc16583fa4d4e7ceb6241444
3
+ size 496817208
tokenized_tamil_CulturaX_dataset/train/data-00015-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d0e46090e0d74100dc5beeee5376bcf28c3c54b258683ae8b52e9812890f4f
3
+ size 495138056
tokenized_tamil_CulturaX_dataset/train/data-00016-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a3220adfdb414e620d371b69fc4ed9f04902da468ae5b0e8e7a89be96a4576
3
+ size 502839768
tokenized_tamil_CulturaX_dataset/train/data-00017-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ddf9997c925fa809e1358c9b6641bdfb6261bbf4ce52e129bba7972c433a9b
3
+ size 500549936
tokenized_tamil_CulturaX_dataset/train/data-00018-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14ea433dbe2879fd658bbea588cdadf643c2ef6331b8026f8817dd922294afc
3
+ size 497750272
tokenized_tamil_CulturaX_dataset/train/data-00019-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:226dd4d794de05f22649e0c4fd40e6dd8b1eff3247f5e9ba301139ed9f57ba01
3
+ size 499247264
tokenized_tamil_CulturaX_dataset/train/data-00020-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581794a85ab4eab8e62ee556a71cf494105045ae2806ddb23833ae2f4fd67b92
3
+ size 493278376
tokenized_tamil_CulturaX_dataset/train/data-00021-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0883fcb3fbbf1182044e4785f1ecf23af209222b646ce22cbbae1d45966bb7ef
3
+ size 495244888
tokenized_tamil_CulturaX_dataset/train/data-00022-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28707191b7b6ac68b30cc402f8fce23a854eaed3695d5207bb4384c2514fe767
3
+ size 503937304
tokenized_tamil_CulturaX_dataset/train/data-00023-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c75fc37600344427261f1189d0bd6157b0bec8ccfbf63810ba7e4b7d6f23f42
3
+ size 492867936
tokenized_tamil_CulturaX_dataset/train/data-00024-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5497e4a1340921761fb77ab3b33a9be942b89cf4ade85aa1a70b9f9b0fe8ce
3
+ size 494700552
tokenized_tamil_CulturaX_dataset/train/data-00025-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71476f07fe5fd58859dfd91866104f26815853f04e97df52900dbdec322d7bba
3
+ size 496562080
tokenized_tamil_CulturaX_dataset/train/data-00026-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f151e7829eed4e30d184efb69b54ce76953d16eb57dda444a9ad04caf1f7b4
3
+ size 495927992
tokenized_tamil_CulturaX_dataset/train/data-00027-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b543ed8aad4a30611f2272c427b9b1d6e042241721651ba349f182f2d462ddf
3
+ size 494564728
tokenized_tamil_CulturaX_dataset/train/data-00028-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72822f16a3587fbe77bf92de8dabaf5f14677344ede86120e39e8735f111903
3
+ size 496818240
tokenized_tamil_CulturaX_dataset/train/data-00029-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e421ab1cad2bc79cb971214a9ff25eb9332fc4ba7f8283621ae7a91207317339
3
+ size 502068472
tokenized_tamil_CulturaX_dataset/train/data-00030-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458f48c79301d4f3f6c44647d55e3e9624134d361ec867ec0239167f51c8f948
3
+ size 496780120
tokenized_tamil_CulturaX_dataset/train/data-00031-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7307df47aed789d120c4655042aa7706356c996626b101915481b71dfb2d0a
3
+ size 500810568
tokenized_tamil_CulturaX_dataset/train/data-00032-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600279e4031af57d1e6f746ec800ce0886541224218c6aa4b178906996f5ae50
3
+ size 501512040
tokenized_tamil_CulturaX_dataset/train/data-00033-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe45fd26b605977541ac08a7ebdb2f8adc03eccf4a7e1eb702b65b384f322de
3
+ size 494778744
tokenized_tamil_CulturaX_dataset/train/data-00034-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c500c2b69b3aa49a069d34f20a532cfea6bb781424044345999d7d4449fd77db
3
+ size 496628840
tokenized_tamil_CulturaX_dataset/train/data-00035-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab86b09cb74d87fa45109947e8c9e9e28efba33abbac1b3d1d7fa4e59e4d8669
3
+ size 498848680
tokenized_tamil_CulturaX_dataset/train/data-00036-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fec74e5e342d5466ccbd1c1de98c555c580950b96659a59cfdda8003f95d006
3
+ size 494516592
tokenized_tamil_CulturaX_dataset/train/data-00037-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ddb23a9ed78d24b0559e3f96a3835406885f74f571ec4876bac4ebf47f1d21
3
+ size 494706152
tokenized_tamil_CulturaX_dataset/train/data-00038-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c264d66c22c260132e95289e1bd82eea7cac80a5a84638cab3aa4a2f75349d
3
+ size 499886680
tokenized_tamil_CulturaX_dataset/train/data-00039-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d413252e8eb76f52c1ca67f26175ece1bdeb2d7832c11547b5f9932c0f18c2
3
+ size 496438128
tokenized_tamil_CulturaX_dataset/train/data-00040-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3421104cc5e1b88f23831863714d7b066974dd3a2f36083a8a56467b28cbc245
3
+ size 497710752
tokenized_tamil_CulturaX_dataset/train/data-00041-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b114b5aaec7dbb1a2f00c528cd3805cdc546e616d6c0f556fe04a738a45a19e
3
+ size 498914256
tokenized_tamil_CulturaX_dataset/train/data-00042-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047f4d85cf130a2d4babea02922822f3cf0adace60c3d7ac6105bc97929f22e9
3
+ size 494177904
tokenized_tamil_CulturaX_dataset/train/data-00043-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c2c608c8478d1d4a185925e8e65605365b7f185daea43dafd0895470aaf3fc
3
+ size 493330896
tokenized_tamil_CulturaX_dataset/train/data-00044-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d057c9ed60f422fde3c758f1e3d0c03ede94b0c8c5ee7840494f9e57c43881
3
+ size 495189992
tokenized_tamil_CulturaX_dataset/train/data-00045-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf6da80c19b227c60ebe56904ef585908705d2d26dbfd1327aca66d2fb095c5
3
+ size 497097816
tokenized_tamil_CulturaX_dataset/train/data-00046-of-00122.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076a029e84d4f8a1f4fb4670366c51edddf41dd1819553c538c129319c98e118
3
+ size 494662432