Hugging Face's logo

TigerResearch
/
tigerbot-180b-base-v2

Text Generation
Transformers
PyTorch
Chinese
English
bloom
text-generation-inference
Inference Endpoints
Model card Files Community
i4never commited on
Commit
cd5709e
·
1 Parent(s): 23c8c0d

Upload BloomForCausalLM

Browse files
Files changed (39) hide show
  1. config.json +26 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00036.bin +3 -0
  4. pytorch_model-00002-of-00036.bin +3 -0
  5. pytorch_model-00003-of-00036.bin +3 -0
  6. pytorch_model-00004-of-00036.bin +3 -0
  7. pytorch_model-00005-of-00036.bin +3 -0
  8. pytorch_model-00006-of-00036.bin +3 -0
  9. pytorch_model-00007-of-00036.bin +3 -0
  10. pytorch_model-00008-of-00036.bin +3 -0
  11. pytorch_model-00009-of-00036.bin +3 -0
  12. pytorch_model-00010-of-00036.bin +3 -0
  13. pytorch_model-00011-of-00036.bin +3 -0
  14. pytorch_model-00012-of-00036.bin +3 -0
  15. pytorch_model-00013-of-00036.bin +3 -0
  16. pytorch_model-00014-of-00036.bin +3 -0
  17. pytorch_model-00015-of-00036.bin +3 -0
  18. pytorch_model-00016-of-00036.bin +3 -0
  19. pytorch_model-00017-of-00036.bin +3 -0
  20. pytorch_model-00018-of-00036.bin +3 -0
  21. pytorch_model-00019-of-00036.bin +3 -0
  22. pytorch_model-00020-of-00036.bin +3 -0
  23. pytorch_model-00021-of-00036.bin +3 -0
  24. pytorch_model-00022-of-00036.bin +3 -0
  25. pytorch_model-00023-of-00036.bin +3 -0
  26. pytorch_model-00024-of-00036.bin +3 -0
  27. pytorch_model-00025-of-00036.bin +3 -0
  28. pytorch_model-00026-of-00036.bin +3 -0
  29. pytorch_model-00027-of-00036.bin +3 -0
  30. pytorch_model-00028-of-00036.bin +3 -0
  31. pytorch_model-00029-of-00036.bin +3 -0
  32. pytorch_model-00030-of-00036.bin +3 -0
  33. pytorch_model-00031-of-00036.bin +3 -0
  34. pytorch_model-00032-of-00036.bin +3 -0
  35. pytorch_model-00033-of-00036.bin +3 -0
  36. pytorch_model-00034-of-00036.bin +3 -0
  37. pytorch_model-00035-of-00036.bin +3 -0
  38. pytorch_model-00036-of-00036.bin +3 -0
  39. pytorch_model.bin.index.json +853 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tigerbot-180b-bloom-base-hf-10500/",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 14336,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "masked_softmax_fusion": true,
16
+ "model_type": "bloom",
17
+ "n_head": 112,
18
+ "n_layer": 70,
19
+ "pad_token_id": 3,
20
+ "pretraining_tp": 4,
21
+ "slow_but_exact": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.34.0",
24
+ "use_cache": true,
25
+ "vocab_size": 250880
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.34.0"
7
+ }
pytorch_model-00001-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3187da2ba70772c77cab754eafd535b0e4a530c5c43ec3449257461ecd30d3
3
+ size 8837690076
pytorch_model-00002-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc9777c81fbd62d2895775cf659f00f0cf6a66d3f65c5e00859ec28e64fa4f5
3
+ size 9865757318
pytorch_model-00003-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b474d55ae804d828ede1dfd59b90b494985d260f7aafcab711165d0060863b84
3
+ size 9865757318
pytorch_model-00004-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a472b3eb2e3a5c6a8d01594f3839ca802a641726b9761853aef72f943a0fdd54
3
+ size 9865757318
pytorch_model-00005-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fade6a15060368fbd037d9638945d71c853534f1ed87e48f6b0cce6663ea348
3
+ size 9865757318
pytorch_model-00006-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3861b788114ac983fec33c8a8f789ce0aac41f8d0c5d69c110abd462c85ea4c
3
+ size 9865757382
pytorch_model-00007-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4cd89630a2725e630b1e13e1db882203474bfcb92ace7620989c1d201104e
3
+ size 9865757382
pytorch_model-00008-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7375b56a1535f88c5f1f488e37212b708369e8b98fbac039497e1b7286e656
3
+ size 9865757382
pytorch_model-00009-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de2e69a9db40b2e2f2441da2cda4e3f90776d9e23850b7425625c491a255aad
3
+ size 9865757382
pytorch_model-00010-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70dee8587d56760414f1f6b5e28de93db450d46e31ef75efede83c3ea438bab4
3
+ size 9865757382
pytorch_model-00011-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136b56084635f1c422cddb5185db34fb80866a84c7170a43cb40db631a230ac6
3
+ size 9865757382
pytorch_model-00012-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fe8957ccaee533e54f97aa95b33eee1c7c2de10424c76142d48ad800de9103
3
+ size 9865757382
pytorch_model-00013-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e583bd86212872a58aba123e0cfd7f96d01186df1823e6e093ea4367c2d2cbd3
3
+ size 9865757382
pytorch_model-00014-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f6c50bb9710c879a791d59974fbc5ce2fc4f5eae1a96f12ca15973bcab7640
3
+ size 9865757382
pytorch_model-00015-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc99c13110b14e03e38e7af312c7aa3d5655dad89afdc6db872aa144fb07c39
3
+ size 9865757382
pytorch_model-00016-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d59dc96927dd17d1945eeaea31d97d5feaa6e3c3dd1b60c638d25a7dd0796bf
3
+ size 9865757382
pytorch_model-00017-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162d15ec31369b932d37a6cd04c85bc546bd350f3235eb096c445587a913e370
3
+ size 9865757382
pytorch_model-00018-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189949529ef7a5533fef059f86de583343e14e9ad8799d0ea67a51890b452cd7
3
+ size 9865757382
pytorch_model-00019-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351623dc9b9131e771f7e995a8b02261547a2a4249f8d8ced7de291f370e6d84
3
+ size 9865757382
pytorch_model-00020-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217f9ea1fc5ff5a7910ea9222ec70fc24a06b2ccfbfc69924c94555d40141986
3
+ size 9865757382
pytorch_model-00021-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d46df3ba9538a5790d2c35264af6516ee9357ba9760216b2d8ec057000b1316
3
+ size 9865757382
pytorch_model-00022-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99aeb8cb6bfce134df868b787c4680439a21d9185add42ff45d067c624841ac
3
+ size 9865757382
pytorch_model-00023-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46f4b50de561c80d3a882c7f8ed498231b89c36919da417d0675fceaf303e62
3
+ size 9865757382
pytorch_model-00024-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f65841392f00a806c3b4b0081befd1260f854cea1d60ab2d87939950b2b2e88
3
+ size 9865757382
pytorch_model-00025-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac5c1abeb05511cf496f47984a0efcce929678bc01352eae240e988cfe15e52
3
+ size 9865757382
pytorch_model-00026-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a952fb468ce32332307880ad7a54deec7119608ce2d02e3556f85626a1d111
3
+ size 9865757382
pytorch_model-00027-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c331a3536db08191b2704dc78c01aeeb62207f2aaf4db0188d3fd4d4553ac96
3
+ size 9865757382
pytorch_model-00028-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c189d575771c8c9e96030f91e3c532ca006c04fc573dd4ac26399f1305e515c0
3
+ size 9865757382
pytorch_model-00029-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d9e5e6c448f8f6e4d8b76c08ccd43f00a28c819111b86b438578bd4793b809c
3
+ size 9865757382
pytorch_model-00030-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666234aee85def980de53cbe63d86922e4371d14e13ba380bd665926cf16260e
3
+ size 9865757382
pytorch_model-00031-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d32da8fbe15f3a8dda294f63d4e1d210796e3a952fc0488c8ff4f2a09666235
3
+ size 9865757382
pytorch_model-00032-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53371c3c0a1e97ed02db8e5a83ab76a038a386724c10522bd05c1ceff9b37908
3
+ size 9865757382
pytorch_model-00033-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647c442ff7fd4896fc2915f4e6f4bd85b12aa4663a5d5d6e1f56bf0b585c3434
3
+ size 9865757382
pytorch_model-00034-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf885237c29d7c83babd2684c9ada2a6227a025e56c3ab6b6d4e5583c47927ee
3
+ size 9865757382
pytorch_model-00035-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb922a126dc39bfe52277d189b8dcb21e56ff50d557e7320b07897972fdd599
3
+ size 9865757382
pytorch_model-00036-of-00036.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96d0d49263134b6ac99130ecef9500ba2eef11c89663362a0f59f39e3285838
3
+ size 8221416146
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,853 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 352494542848
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00036.bin",
7
+ "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00036.bin",
8
+ "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00036.bin",
9
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00036.bin",
10
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00036.bin",
11
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00036.bin",
12
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00036.bin",
13
+ "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00036.bin",
14
+ "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00036.bin",
15
+ "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00036.bin",
16
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00036.bin",
17
+ "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00036.bin",
18
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00036.bin",
19
+ "transformer.h.1.input_layernorm.bias": "pytorch_model-00002-of-00036.bin",
20
+ "transformer.h.1.input_layernorm.weight": "pytorch_model-00002-of-00036.bin",
21
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00036.bin",
22
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00036.bin",
23
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00036.bin",
24
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00036.bin",
25
+ "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00036.bin",
26
+ "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00036.bin",
27
+ "transformer.h.1.self_attention.dense.bias": "pytorch_model-00002-of-00036.bin",
28
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00002-of-00036.bin",
29
+ "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00002-of-00036.bin",
30
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00002-of-00036.bin",
31
+ "transformer.h.10.input_layernorm.bias": "pytorch_model-00006-of-00036.bin",
32
+ "transformer.h.10.input_layernorm.weight": "pytorch_model-00006-of-00036.bin",
33
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00036.bin",
34
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00036.bin",
35
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00036.bin",
36
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00036.bin",
37
+ "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00006-of-00036.bin",
38
+ "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00036.bin",
39
+ "transformer.h.10.self_attention.dense.bias": "pytorch_model-00006-of-00036.bin",
40
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00006-of-00036.bin",
41
+ "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00006-of-00036.bin",
42
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00006-of-00036.bin",
43
+ "transformer.h.11.input_layernorm.bias": "pytorch_model-00007-of-00036.bin",
44
+ "transformer.h.11.input_layernorm.weight": "pytorch_model-00007-of-00036.bin",
45
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00036.bin",
46
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00036.bin",
47
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00036.bin",
48
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00036.bin",
49
+ "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00007-of-00036.bin",
50
+ "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00036.bin",
51
+ "transformer.h.11.self_attention.dense.bias": "pytorch_model-00007-of-00036.bin",
52
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00007-of-00036.bin",
53
+ "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00007-of-00036.bin",
54
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00007-of-00036.bin",
55
+ "transformer.h.12.input_layernorm.bias": "pytorch_model-00007-of-00036.bin",
56
+ "transformer.h.12.input_layernorm.weight": "pytorch_model-00007-of-00036.bin",
57
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00036.bin",
58
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00036.bin",
59
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00036.bin",
60
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00036.bin",
61
+ "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00007-of-00036.bin",
62
+ "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00036.bin",
63
+ "transformer.h.12.self_attention.dense.bias": "pytorch_model-00007-of-00036.bin",
64
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00007-of-00036.bin",
65
+ "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00007-of-00036.bin",
66
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00007-of-00036.bin",
67
+ "transformer.h.13.input_layernorm.bias": "pytorch_model-00008-of-00036.bin",
68
+ "transformer.h.13.input_layernorm.weight": "pytorch_model-00008-of-00036.bin",
69
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00036.bin",
70
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00036.bin",
71
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00036.bin",
72
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00036.bin",
73
+ "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00008-of-00036.bin",
74
+ "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00008-of-00036.bin",
75
+ "transformer.h.13.self_attention.dense.bias": "pytorch_model-00008-of-00036.bin",
76
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00008-of-00036.bin",
77
+ "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00008-of-00036.bin",
78
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00008-of-00036.bin",
79
+ "transformer.h.14.input_layernorm.bias": "pytorch_model-00008-of-00036.bin",
80
+ "transformer.h.14.input_layernorm.weight": "pytorch_model-00008-of-00036.bin",
81
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00036.bin",
82
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00036.bin",
83
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00036.bin",
84
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00036.bin",
85
+ "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00008-of-00036.bin",
86
+ "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00036.bin",
87
+ "transformer.h.14.self_attention.dense.bias": "pytorch_model-00008-of-00036.bin",
88
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00008-of-00036.bin",
89
+ "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00008-of-00036.bin",
90
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00008-of-00036.bin",
91
+ "transformer.h.15.input_layernorm.bias": "pytorch_model-00009-of-00036.bin",
92
+ "transformer.h.15.input_layernorm.weight": "pytorch_model-00009-of-00036.bin",
93
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00036.bin",
94
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00036.bin",
95
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00036.bin",
96
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00036.bin",
97
+ "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00009-of-00036.bin",
98
+ "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00009-of-00036.bin",
99
+ "transformer.h.15.self_attention.dense.bias": "pytorch_model-00009-of-00036.bin",
100
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00009-of-00036.bin",
101
+ "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00009-of-00036.bin",
102
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00009-of-00036.bin",
103
+ "transformer.h.16.input_layernorm.bias": "pytorch_model-00009-of-00036.bin",
104
+ "transformer.h.16.input_layernorm.weight": "pytorch_model-00009-of-00036.bin",
105
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00036.bin",
106
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00036.bin",
107
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00036.bin",
108
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00036.bin",
109
+ "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00009-of-00036.bin",
110
+ "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00036.bin",
111
+ "transformer.h.16.self_attention.dense.bias": "pytorch_model-00009-of-00036.bin",
112
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00009-of-00036.bin",
113
+ "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00009-of-00036.bin",
114
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00009-of-00036.bin",
115
+ "transformer.h.17.input_layernorm.bias": "pytorch_model-00010-of-00036.bin",
116
+ "transformer.h.17.input_layernorm.weight": "pytorch_model-00010-of-00036.bin",
117
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00036.bin",
118
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00036.bin",
119
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00036.bin",
120
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00036.bin",
121
+ "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00010-of-00036.bin",
122
+ "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00010-of-00036.bin",
123
+ "transformer.h.17.self_attention.dense.bias": "pytorch_model-00010-of-00036.bin",
124
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00010-of-00036.bin",
125
+ "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00010-of-00036.bin",
126
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00010-of-00036.bin",
127
+ "transformer.h.18.input_layernorm.bias": "pytorch_model-00010-of-00036.bin",
128
+ "transformer.h.18.input_layernorm.weight": "pytorch_model-00010-of-00036.bin",
129
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00036.bin",
130
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00036.bin",
131
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00036.bin",
132
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00036.bin",
133
+ "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00010-of-00036.bin",
134
+ "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00036.bin",
135
+ "transformer.h.18.self_attention.dense.bias": "pytorch_model-00010-of-00036.bin",
136
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00010-of-00036.bin",
137
+ "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00010-of-00036.bin",
138
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00010-of-00036.bin",
139
+ "transformer.h.19.input_layernorm.bias": "pytorch_model-00011-of-00036.bin",
140
+ "transformer.h.19.input_layernorm.weight": "pytorch_model-00011-of-00036.bin",
141
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00036.bin",
142
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00036.bin",
143
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00036.bin",
144
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00036.bin",
145
+ "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00011-of-00036.bin",
146
+ "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00011-of-00036.bin",
147
+ "transformer.h.19.self_attention.dense.bias": "pytorch_model-00011-of-00036.bin",
148
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00011-of-00036.bin",
149
+ "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00011-of-00036.bin",
150
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00011-of-00036.bin",
151
+ "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00036.bin",
152
+ "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00036.bin",
153
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00036.bin",
154
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00036.bin",
155
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00036.bin",
156
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00036.bin",
157
+ "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00036.bin",
158
+ "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00036.bin",
159
+ "transformer.h.2.self_attention.dense.bias": "pytorch_model-00002-of-00036.bin",
160
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00036.bin",
161
+ "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00036.bin",
162
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00036.bin",
163
+ "transformer.h.20.input_layernorm.bias": "pytorch_model-00011-of-00036.bin",
164
+ "transformer.h.20.input_layernorm.weight": "pytorch_model-00011-of-00036.bin",
165
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00036.bin",
166
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00036.bin",
167
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00036.bin",
168
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00036.bin",
169
+ "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00011-of-00036.bin",
170
+ "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00011-of-00036.bin",
171
+ "transformer.h.20.self_attention.dense.bias": "pytorch_model-00011-of-00036.bin",
172
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00011-of-00036.bin",
173
+ "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00011-of-00036.bin",
174
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00011-of-00036.bin",
175
+ "transformer.h.21.input_layernorm.bias": "pytorch_model-00012-of-00036.bin",
176
+ "transformer.h.21.input_layernorm.weight": "pytorch_model-00012-of-00036.bin",
177
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00036.bin",
178
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00036.bin",
179
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00036.bin",
180
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00036.bin",
181
+ "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00012-of-00036.bin",
182
+ "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00012-of-00036.bin",
183
+ "transformer.h.21.self_attention.dense.bias": "pytorch_model-00012-of-00036.bin",
184
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00012-of-00036.bin",
185
+ "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00012-of-00036.bin",
186
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00012-of-00036.bin",
187
+ "transformer.h.22.input_layernorm.bias": "pytorch_model-00012-of-00036.bin",
188
+ "transformer.h.22.input_layernorm.weight": "pytorch_model-00012-of-00036.bin",
189
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00036.bin",
190
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00036.bin",
191
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00036.bin",
192
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00036.bin",
193
+ "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00012-of-00036.bin",
194
+ "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00012-of-00036.bin",
195
+ "transformer.h.22.self_attention.dense.bias": "pytorch_model-00012-of-00036.bin",
196
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00012-of-00036.bin",
197
+ "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00012-of-00036.bin",
198
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00012-of-00036.bin",
199
+ "transformer.h.23.input_layernorm.bias": "pytorch_model-00013-of-00036.bin",
200
+ "transformer.h.23.input_layernorm.weight": "pytorch_model-00013-of-00036.bin",
201
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00036.bin",
202
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00036.bin",
203
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00036.bin",
204
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00036.bin",
205
+ "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00013-of-00036.bin",
206
+ "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00013-of-00036.bin",
207
+ "transformer.h.23.self_attention.dense.bias": "pytorch_model-00013-of-00036.bin",
208
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00013-of-00036.bin",
209
+ "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00013-of-00036.bin",
210
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00013-of-00036.bin",
211
+ "transformer.h.24.input_layernorm.bias": "pytorch_model-00013-of-00036.bin",
212
+ "transformer.h.24.input_layernorm.weight": "pytorch_model-00013-of-00036.bin",
213
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00036.bin",
214
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00036.bin",
215
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00036.bin",
216
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00036.bin",
217
+ "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00013-of-00036.bin",
218
+ "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00013-of-00036.bin",
219
+ "transformer.h.24.self_attention.dense.bias": "pytorch_model-00013-of-00036.bin",
220
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00013-of-00036.bin",
221
+ "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00013-of-00036.bin",
222
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00013-of-00036.bin",
223
+ "transformer.h.25.input_layernorm.bias": "pytorch_model-00014-of-00036.bin",
224
+ "transformer.h.25.input_layernorm.weight": "pytorch_model-00014-of-00036.bin",
225
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00036.bin",
226
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00036.bin",
227
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00036.bin",
228
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00036.bin",
229
+ "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00014-of-00036.bin",
230
+ "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00014-of-00036.bin",
231
+ "transformer.h.25.self_attention.dense.bias": "pytorch_model-00014-of-00036.bin",
232
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00014-of-00036.bin",
233
+ "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00014-of-00036.bin",
234
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00014-of-00036.bin",
235
+ "transformer.h.26.input_layernorm.bias": "pytorch_model-00014-of-00036.bin",
236
+ "transformer.h.26.input_layernorm.weight": "pytorch_model-00014-of-00036.bin",
237
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00036.bin",
238
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00036.bin",
239
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00036.bin",
240
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00036.bin",
241
+ "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00014-of-00036.bin",
242
+ "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00014-of-00036.bin",
243
+ "transformer.h.26.self_attention.dense.bias": "pytorch_model-00014-of-00036.bin",
244
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00014-of-00036.bin",
245
+ "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00014-of-00036.bin",
246
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00014-of-00036.bin",
247
+ "transformer.h.27.input_layernorm.bias": "pytorch_model-00015-of-00036.bin",
248
+ "transformer.h.27.input_layernorm.weight": "pytorch_model-00015-of-00036.bin",
249
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00036.bin",
250
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00036.bin",
251
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00036.bin",
252
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00036.bin",
253
+ "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00015-of-00036.bin",
254
+ "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00015-of-00036.bin",
255
+ "transformer.h.27.self_attention.dense.bias": "pytorch_model-00015-of-00036.bin",
256
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00015-of-00036.bin",
257
+ "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00015-of-00036.bin",
258
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00015-of-00036.bin",
259
+ "transformer.h.28.input_layernorm.bias": "pytorch_model-00015-of-00036.bin",
260
+ "transformer.h.28.input_layernorm.weight": "pytorch_model-00015-of-00036.bin",
261
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00036.bin",
262
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00036.bin",
263
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00036.bin",
264
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00036.bin",
265
+ "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00015-of-00036.bin",
266
+ "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00015-of-00036.bin",
267
+ "transformer.h.28.self_attention.dense.bias": "pytorch_model-00015-of-00036.bin",
268
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00015-of-00036.bin",
269
+ "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00015-of-00036.bin",
270
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00015-of-00036.bin",
271
+ "transformer.h.29.input_layernorm.bias": "pytorch_model-00016-of-00036.bin",
272
+ "transformer.h.29.input_layernorm.weight": "pytorch_model-00016-of-00036.bin",
273
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00036.bin",
274
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00036.bin",
275
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00036.bin",
276
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00036.bin",
277
+ "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00016-of-00036.bin",
278
+ "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00016-of-00036.bin",
279
+ "transformer.h.29.self_attention.dense.bias": "pytorch_model-00016-of-00036.bin",
280
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00016-of-00036.bin",
281
+ "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00016-of-00036.bin",
282
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00016-of-00036.bin",
283
+ "transformer.h.3.input_layernorm.bias": "pytorch_model-00003-of-00036.bin",
284
+ "transformer.h.3.input_layernorm.weight": "pytorch_model-00003-of-00036.bin",
285
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00036.bin",
286
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00036.bin",
287
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00036.bin",
288
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00036.bin",
289
+ "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00003-of-00036.bin",
290
+ "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00036.bin",
291
+ "transformer.h.3.self_attention.dense.bias": "pytorch_model-00003-of-00036.bin",
292
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00003-of-00036.bin",
293
+ "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00003-of-00036.bin",
294
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00003-of-00036.bin",
295
+ "transformer.h.30.input_layernorm.bias": "pytorch_model-00016-of-00036.bin",
296
+ "transformer.h.30.input_layernorm.weight": "pytorch_model-00016-of-00036.bin",
297
+ "transformer.h.30.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00036.bin",
298
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00036.bin",
299
+ "transformer.h.30.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00036.bin",
300
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00036.bin",
301
+ "transformer.h.30.post_attention_layernorm.bias": "pytorch_model-00016-of-00036.bin",
302
+ "transformer.h.30.post_attention_layernorm.weight": "pytorch_model-00016-of-00036.bin",
303
+ "transformer.h.30.self_attention.dense.bias": "pytorch_model-00016-of-00036.bin",
304
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00016-of-00036.bin",
305
+ "transformer.h.30.self_attention.query_key_value.bias": "pytorch_model-00016-of-00036.bin",
306
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00016-of-00036.bin",
307
+ "transformer.h.31.input_layernorm.bias": "pytorch_model-00017-of-00036.bin",
308
+ "transformer.h.31.input_layernorm.weight": "pytorch_model-00017-of-00036.bin",
309
+ "transformer.h.31.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00036.bin",
310
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00036.bin",
311
+ "transformer.h.31.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00036.bin",
312
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00036.bin",
313
+ "transformer.h.31.post_attention_layernorm.bias": "pytorch_model-00017-of-00036.bin",
314
+ "transformer.h.31.post_attention_layernorm.weight": "pytorch_model-00017-of-00036.bin",
315
+ "transformer.h.31.self_attention.dense.bias": "pytorch_model-00017-of-00036.bin",
316
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00017-of-00036.bin",
317
+ "transformer.h.31.self_attention.query_key_value.bias": "pytorch_model-00017-of-00036.bin",
318
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00017-of-00036.bin",
319
+ "transformer.h.32.input_layernorm.bias": "pytorch_model-00017-of-00036.bin",
320
+ "transformer.h.32.input_layernorm.weight": "pytorch_model-00017-of-00036.bin",
321
+ "transformer.h.32.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00036.bin",
322
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00036.bin",
323
+ "transformer.h.32.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00036.bin",
324
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00036.bin",
325
+ "transformer.h.32.post_attention_layernorm.bias": "pytorch_model-00017-of-00036.bin",
326
+ "transformer.h.32.post_attention_layernorm.weight": "pytorch_model-00017-of-00036.bin",
327
+ "transformer.h.32.self_attention.dense.bias": "pytorch_model-00017-of-00036.bin",
328
+ "transformer.h.32.self_attention.dense.weight": "pytorch_model-00017-of-00036.bin",
329
+ "transformer.h.32.self_attention.query_key_value.bias": "pytorch_model-00017-of-00036.bin",
330
+ "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00017-of-00036.bin",
331
+ "transformer.h.33.input_layernorm.bias": "pytorch_model-00018-of-00036.bin",
332
+ "transformer.h.33.input_layernorm.weight": "pytorch_model-00018-of-00036.bin",
333
+ "transformer.h.33.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00036.bin",
334
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00036.bin",
335
+ "transformer.h.33.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00036.bin",
336
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00036.bin",
337
+ "transformer.h.33.post_attention_layernorm.bias": "pytorch_model-00018-of-00036.bin",
338
+ "transformer.h.33.post_attention_layernorm.weight": "pytorch_model-00018-of-00036.bin",
339
+ "transformer.h.33.self_attention.dense.bias": "pytorch_model-00018-of-00036.bin",
340
+ "transformer.h.33.self_attention.dense.weight": "pytorch_model-00018-of-00036.bin",
341
+ "transformer.h.33.self_attention.query_key_value.bias": "pytorch_model-00018-of-00036.bin",
342
+ "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00018-of-00036.bin",
343
+ "transformer.h.34.input_layernorm.bias": "pytorch_model-00018-of-00036.bin",
344
+ "transformer.h.34.input_layernorm.weight": "pytorch_model-00018-of-00036.bin",
345
+ "transformer.h.34.mlp.dense_4h_to_h.bias": "pytorch_model-00019-of-00036.bin",
346
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00036.bin",
347
+ "transformer.h.34.mlp.dense_h_to_4h.bias": "pytorch_model-00019-of-00036.bin",
348
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00036.bin",
349
+ "transformer.h.34.post_attention_layernorm.bias": "pytorch_model-00018-of-00036.bin",
350
+ "transformer.h.34.post_attention_layernorm.weight": "pytorch_model-00018-of-00036.bin",
351
+ "transformer.h.34.self_attention.dense.bias": "pytorch_model-00018-of-00036.bin",
352
+ "transformer.h.34.self_attention.dense.weight": "pytorch_model-00018-of-00036.bin",
353
+ "transformer.h.34.self_attention.query_key_value.bias": "pytorch_model-00018-of-00036.bin",
354
+ "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00018-of-00036.bin",
355
+ "transformer.h.35.input_layernorm.bias": "pytorch_model-00019-of-00036.bin",
356
+ "transformer.h.35.input_layernorm.weight": "pytorch_model-00019-of-00036.bin",
357
+ "transformer.h.35.mlp.dense_4h_to_h.bias": "pytorch_model-00019-of-00036.bin",
358
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00036.bin",
359
+ "transformer.h.35.mlp.dense_h_to_4h.bias": "pytorch_model-00019-of-00036.bin",
360
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00036.bin",
361
+ "transformer.h.35.post_attention_layernorm.bias": "pytorch_model-00019-of-00036.bin",
362
+ "transformer.h.35.post_attention_layernorm.weight": "pytorch_model-00019-of-00036.bin",
363
+ "transformer.h.35.self_attention.dense.bias": "pytorch_model-00019-of-00036.bin",
364
+ "transformer.h.35.self_attention.dense.weight": "pytorch_model-00019-of-00036.bin",
365
+ "transformer.h.35.self_attention.query_key_value.bias": "pytorch_model-00019-of-00036.bin",
366
+ "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00019-of-00036.bin",
367
+ "transformer.h.36.input_layernorm.bias": "pytorch_model-00019-of-00036.bin",
368
+ "transformer.h.36.input_layernorm.weight": "pytorch_model-00019-of-00036.bin",
369
+ "transformer.h.36.mlp.dense_4h_to_h.bias": "pytorch_model-00020-of-00036.bin",
370
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00036.bin",
371
+ "transformer.h.36.mlp.dense_h_to_4h.bias": "pytorch_model-00020-of-00036.bin",
372
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00036.bin",
373
+ "transformer.h.36.post_attention_layernorm.bias": "pytorch_model-00019-of-00036.bin",
374
+ "transformer.h.36.post_attention_layernorm.weight": "pytorch_model-00019-of-00036.bin",
375
+ "transformer.h.36.self_attention.dense.bias": "pytorch_model-00019-of-00036.bin",
376
+ "transformer.h.36.self_attention.dense.weight": "pytorch_model-00019-of-00036.bin",
377
+ "transformer.h.36.self_attention.query_key_value.bias": "pytorch_model-00019-of-00036.bin",
378
+ "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00019-of-00036.bin",
379
+ "transformer.h.37.input_layernorm.bias": "pytorch_model-00020-of-00036.bin",
380
+ "transformer.h.37.input_layernorm.weight": "pytorch_model-00020-of-00036.bin",
381
+ "transformer.h.37.mlp.dense_4h_to_h.bias": "pytorch_model-00020-of-00036.bin",
382
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00036.bin",
383
+ "transformer.h.37.mlp.dense_h_to_4h.bias": "pytorch_model-00020-of-00036.bin",
384
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00036.bin",
385
+ "transformer.h.37.post_attention_layernorm.bias": "pytorch_model-00020-of-00036.bin",
386
+ "transformer.h.37.post_attention_layernorm.weight": "pytorch_model-00020-of-00036.bin",
387
+ "transformer.h.37.self_attention.dense.bias": "pytorch_model-00020-of-00036.bin",
388
+ "transformer.h.37.self_attention.dense.weight": "pytorch_model-00020-of-00036.bin",
389
+ "transformer.h.37.self_attention.query_key_value.bias": "pytorch_model-00020-of-00036.bin",
390
+ "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00020-of-00036.bin",
391
+ "transformer.h.38.input_layernorm.bias": "pytorch_model-00020-of-00036.bin",
392
+ "transformer.h.38.input_layernorm.weight": "pytorch_model-00020-of-00036.bin",
393
+ "transformer.h.38.mlp.dense_4h_to_h.bias": "pytorch_model-00021-of-00036.bin",
394
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00036.bin",
395
+ "transformer.h.38.mlp.dense_h_to_4h.bias": "pytorch_model-00021-of-00036.bin",
396
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00036.bin",
397
+ "transformer.h.38.post_attention_layernorm.bias": "pytorch_model-00020-of-00036.bin",
398
+ "transformer.h.38.post_attention_layernorm.weight": "pytorch_model-00020-of-00036.bin",
399
+ "transformer.h.38.self_attention.dense.bias": "pytorch_model-00020-of-00036.bin",
400
+ "transformer.h.38.self_attention.dense.weight": "pytorch_model-00020-of-00036.bin",
401
+ "transformer.h.38.self_attention.query_key_value.bias": "pytorch_model-00020-of-00036.bin",
402
+ "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00020-of-00036.bin",
403
+ "transformer.h.39.input_layernorm.bias": "pytorch_model-00021-of-00036.bin",
404
+ "transformer.h.39.input_layernorm.weight": "pytorch_model-00021-of-00036.bin",
405
+ "transformer.h.39.mlp.dense_4h_to_h.bias": "pytorch_model-00021-of-00036.bin",
406
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00036.bin",
407
+ "transformer.h.39.mlp.dense_h_to_4h.bias": "pytorch_model-00021-of-00036.bin",
408
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00036.bin",
409
+ "transformer.h.39.post_attention_layernorm.bias": "pytorch_model-00021-of-00036.bin",
410
+ "transformer.h.39.post_attention_layernorm.weight": "pytorch_model-00021-of-00036.bin",
411
+ "transformer.h.39.self_attention.dense.bias": "pytorch_model-00021-of-00036.bin",
412
+ "transformer.h.39.self_attention.dense.weight": "pytorch_model-00021-of-00036.bin",
413
+ "transformer.h.39.self_attention.query_key_value.bias": "pytorch_model-00021-of-00036.bin",
414
+ "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00021-of-00036.bin",
415
+ "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00036.bin",
416
+ "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00036.bin",
417
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00036.bin",
418
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00036.bin",
419
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00036.bin",
420
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00036.bin",
421
+ "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00036.bin",
422
+ "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00036.bin",
423
+ "transformer.h.4.self_attention.dense.bias": "pytorch_model-00003-of-00036.bin",
424
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00036.bin",
425
+ "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00003-of-00036.bin",
426
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00036.bin",
427
+ "transformer.h.40.input_layernorm.bias": "pytorch_model-00021-of-00036.bin",
428
+ "transformer.h.40.input_layernorm.weight": "pytorch_model-00021-of-00036.bin",
429
+ "transformer.h.40.mlp.dense_4h_to_h.bias": "pytorch_model-00022-of-00036.bin",
430
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00036.bin",
431
+ "transformer.h.40.mlp.dense_h_to_4h.bias": "pytorch_model-00022-of-00036.bin",
432
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00036.bin",
433
+ "transformer.h.40.post_attention_layernorm.bias": "pytorch_model-00021-of-00036.bin",
434
+ "transformer.h.40.post_attention_layernorm.weight": "pytorch_model-00021-of-00036.bin",
435
+ "transformer.h.40.self_attention.dense.bias": "pytorch_model-00021-of-00036.bin",
436
+ "transformer.h.40.self_attention.dense.weight": "pytorch_model-00021-of-00036.bin",
437
+ "transformer.h.40.self_attention.query_key_value.bias": "pytorch_model-00021-of-00036.bin",
438
+ "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00021-of-00036.bin",
439
+ "transformer.h.41.input_layernorm.bias": "pytorch_model-00022-of-00036.bin",
440
+ "transformer.h.41.input_layernorm.weight": "pytorch_model-00022-of-00036.bin",
441
+ "transformer.h.41.mlp.dense_4h_to_h.bias": "pytorch_model-00022-of-00036.bin",
442
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00036.bin",
443
+ "transformer.h.41.mlp.dense_h_to_4h.bias": "pytorch_model-00022-of-00036.bin",
444
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00036.bin",
445
+ "transformer.h.41.post_attention_layernorm.bias": "pytorch_model-00022-of-00036.bin",
446
+ "transformer.h.41.post_attention_layernorm.weight": "pytorch_model-00022-of-00036.bin",
447
+ "transformer.h.41.self_attention.dense.bias": "pytorch_model-00022-of-00036.bin",
448
+ "transformer.h.41.self_attention.dense.weight": "pytorch_model-00022-of-00036.bin",
449
+ "transformer.h.41.self_attention.query_key_value.bias": "pytorch_model-00022-of-00036.bin",
450
+ "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00022-of-00036.bin",
451
+ "transformer.h.42.input_layernorm.bias": "pytorch_model-00022-of-00036.bin",
452
+ "transformer.h.42.input_layernorm.weight": "pytorch_model-00022-of-00036.bin",
453
+ "transformer.h.42.mlp.dense_4h_to_h.bias": "pytorch_model-00023-of-00036.bin",
454
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00036.bin",
455
+ "transformer.h.42.mlp.dense_h_to_4h.bias": "pytorch_model-00023-of-00036.bin",
456
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00036.bin",
457
+ "transformer.h.42.post_attention_layernorm.bias": "pytorch_model-00022-of-00036.bin",
458
+ "transformer.h.42.post_attention_layernorm.weight": "pytorch_model-00022-of-00036.bin",
459
+ "transformer.h.42.self_attention.dense.bias": "pytorch_model-00022-of-00036.bin",
460
+ "transformer.h.42.self_attention.dense.weight": "pytorch_model-00022-of-00036.bin",
461
+ "transformer.h.42.self_attention.query_key_value.bias": "pytorch_model-00022-of-00036.bin",
462
+ "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00022-of-00036.bin",
463
+ "transformer.h.43.input_layernorm.bias": "pytorch_model-00023-of-00036.bin",
464
+ "transformer.h.43.input_layernorm.weight": "pytorch_model-00023-of-00036.bin",
465
+ "transformer.h.43.mlp.dense_4h_to_h.bias": "pytorch_model-00023-of-00036.bin",
466
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00036.bin",
467
+ "transformer.h.43.mlp.dense_h_to_4h.bias": "pytorch_model-00023-of-00036.bin",
468
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00036.bin",
469
+ "transformer.h.43.post_attention_layernorm.bias": "pytorch_model-00023-of-00036.bin",
470
+ "transformer.h.43.post_attention_layernorm.weight": "pytorch_model-00023-of-00036.bin",
471
+ "transformer.h.43.self_attention.dense.bias": "pytorch_model-00023-of-00036.bin",
472
+ "transformer.h.43.self_attention.dense.weight": "pytorch_model-00023-of-00036.bin",
473
+ "transformer.h.43.self_attention.query_key_value.bias": "pytorch_model-00023-of-00036.bin",
474
+ "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00023-of-00036.bin",
475
+ "transformer.h.44.input_layernorm.bias": "pytorch_model-00023-of-00036.bin",
476
+ "transformer.h.44.input_layernorm.weight": "pytorch_model-00023-of-00036.bin",
477
+ "transformer.h.44.mlp.dense_4h_to_h.bias": "pytorch_model-00024-of-00036.bin",
478
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00036.bin",
479
+ "transformer.h.44.mlp.dense_h_to_4h.bias": "pytorch_model-00024-of-00036.bin",
480
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00036.bin",
481
+ "transformer.h.44.post_attention_layernorm.bias": "pytorch_model-00023-of-00036.bin",
482
+ "transformer.h.44.post_attention_layernorm.weight": "pytorch_model-00023-of-00036.bin",
483
+ "transformer.h.44.self_attention.dense.bias": "pytorch_model-00023-of-00036.bin",
484
+ "transformer.h.44.self_attention.dense.weight": "pytorch_model-00023-of-00036.bin",
485
+ "transformer.h.44.self_attention.query_key_value.bias": "pytorch_model-00023-of-00036.bin",
486
+ "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00023-of-00036.bin",
487
+ "transformer.h.45.input_layernorm.bias": "pytorch_model-00024-of-00036.bin",
488
+ "transformer.h.45.input_layernorm.weight": "pytorch_model-00024-of-00036.bin",
489
+ "transformer.h.45.mlp.dense_4h_to_h.bias": "pytorch_model-00024-of-00036.bin",
490
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00036.bin",
491
+ "transformer.h.45.mlp.dense_h_to_4h.bias": "pytorch_model-00024-of-00036.bin",
492
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00036.bin",
493
+ "transformer.h.45.post_attention_layernorm.bias": "pytorch_model-00024-of-00036.bin",
494
+ "transformer.h.45.post_attention_layernorm.weight": "pytorch_model-00024-of-00036.bin",
495
+ "transformer.h.45.self_attention.dense.bias": "pytorch_model-00024-of-00036.bin",
496
+ "transformer.h.45.self_attention.dense.weight": "pytorch_model-00024-of-00036.bin",
497
+ "transformer.h.45.self_attention.query_key_value.bias": "pytorch_model-00024-of-00036.bin",
498
+ "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00024-of-00036.bin",
499
+ "transformer.h.46.input_layernorm.bias": "pytorch_model-00024-of-00036.bin",
500
+ "transformer.h.46.input_layernorm.weight": "pytorch_model-00024-of-00036.bin",
501
+ "transformer.h.46.mlp.dense_4h_to_h.bias": "pytorch_model-00025-of-00036.bin",
502
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00036.bin",
503
+ "transformer.h.46.mlp.dense_h_to_4h.bias": "pytorch_model-00025-of-00036.bin",
504
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00036.bin",
505
+ "transformer.h.46.post_attention_layernorm.bias": "pytorch_model-00024-of-00036.bin",
506
+ "transformer.h.46.post_attention_layernorm.weight": "pytorch_model-00024-of-00036.bin",
507
+ "transformer.h.46.self_attention.dense.bias": "pytorch_model-00024-of-00036.bin",
508
+ "transformer.h.46.self_attention.dense.weight": "pytorch_model-00024-of-00036.bin",
509
+ "transformer.h.46.self_attention.query_key_value.bias": "pytorch_model-00024-of-00036.bin",
510
+ "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00024-of-00036.bin",
511
+ "transformer.h.47.input_layernorm.bias": "pytorch_model-00025-of-00036.bin",
512
+ "transformer.h.47.input_layernorm.weight": "pytorch_model-00025-of-00036.bin",
513
+ "transformer.h.47.mlp.dense_4h_to_h.bias": "pytorch_model-00025-of-00036.bin",
514
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00036.bin",
515
+ "transformer.h.47.mlp.dense_h_to_4h.bias": "pytorch_model-00025-of-00036.bin",
516
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00036.bin",
517
+ "transformer.h.47.post_attention_layernorm.bias": "pytorch_model-00025-of-00036.bin",
518
+ "transformer.h.47.post_attention_layernorm.weight": "pytorch_model-00025-of-00036.bin",
519
+ "transformer.h.47.self_attention.dense.bias": "pytorch_model-00025-of-00036.bin",
520
+ "transformer.h.47.self_attention.dense.weight": "pytorch_model-00025-of-00036.bin",
521
+ "transformer.h.47.self_attention.query_key_value.bias": "pytorch_model-00025-of-00036.bin",
522
+ "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00025-of-00036.bin",
523
+ "transformer.h.48.input_layernorm.bias": "pytorch_model-00025-of-00036.bin",
524
+ "transformer.h.48.input_layernorm.weight": "pytorch_model-00025-of-00036.bin",
525
+ "transformer.h.48.mlp.dense_4h_to_h.bias": "pytorch_model-00026-of-00036.bin",
526
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00036.bin",
527
+ "transformer.h.48.mlp.dense_h_to_4h.bias": "pytorch_model-00026-of-00036.bin",
528
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00036.bin",
529
+ "transformer.h.48.post_attention_layernorm.bias": "pytorch_model-00025-of-00036.bin",
530
+ "transformer.h.48.post_attention_layernorm.weight": "pytorch_model-00025-of-00036.bin",
531
+ "transformer.h.48.self_attention.dense.bias": "pytorch_model-00025-of-00036.bin",
532
+ "transformer.h.48.self_attention.dense.weight": "pytorch_model-00025-of-00036.bin",
533
+ "transformer.h.48.self_attention.query_key_value.bias": "pytorch_model-00025-of-00036.bin",
534
+ "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00025-of-00036.bin",
535
+ "transformer.h.49.input_layernorm.bias": "pytorch_model-00026-of-00036.bin",
536
+ "transformer.h.49.input_layernorm.weight": "pytorch_model-00026-of-00036.bin",
537
+ "transformer.h.49.mlp.dense_4h_to_h.bias": "pytorch_model-00026-of-00036.bin",
538
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00036.bin",
539
+ "transformer.h.49.mlp.dense_h_to_4h.bias": "pytorch_model-00026-of-00036.bin",
540
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00036.bin",
541
+ "transformer.h.49.post_attention_layernorm.bias": "pytorch_model-00026-of-00036.bin",
542
+ "transformer.h.49.post_attention_layernorm.weight": "pytorch_model-00026-of-00036.bin",
543
+ "transformer.h.49.self_attention.dense.bias": "pytorch_model-00026-of-00036.bin",
544
+ "transformer.h.49.self_attention.dense.weight": "pytorch_model-00026-of-00036.bin",
545
+ "transformer.h.49.self_attention.query_key_value.bias": "pytorch_model-00026-of-00036.bin",
546
+ "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00026-of-00036.bin",
547
+ "transformer.h.5.input_layernorm.bias": "pytorch_model-00004-of-00036.bin",
548
+ "transformer.h.5.input_layernorm.weight": "pytorch_model-00004-of-00036.bin",
549
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00036.bin",
550
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00036.bin",
551
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00036.bin",
552
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00036.bin",
553
+ "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00004-of-00036.bin",
554
+ "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00036.bin",
555
+ "transformer.h.5.self_attention.dense.bias": "pytorch_model-00004-of-00036.bin",
556
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00004-of-00036.bin",
557
+ "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00004-of-00036.bin",
558
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00004-of-00036.bin",
559
+ "transformer.h.50.input_layernorm.bias": "pytorch_model-00026-of-00036.bin",
560
+ "transformer.h.50.input_layernorm.weight": "pytorch_model-00026-of-00036.bin",
561
+ "transformer.h.50.mlp.dense_4h_to_h.bias": "pytorch_model-00027-of-00036.bin",
562
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00036.bin",
563
+ "transformer.h.50.mlp.dense_h_to_4h.bias": "pytorch_model-00027-of-00036.bin",
564
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00036.bin",
565
+ "transformer.h.50.post_attention_layernorm.bias": "pytorch_model-00026-of-00036.bin",
566
+ "transformer.h.50.post_attention_layernorm.weight": "pytorch_model-00026-of-00036.bin",
567
+ "transformer.h.50.self_attention.dense.bias": "pytorch_model-00026-of-00036.bin",
568
+ "transformer.h.50.self_attention.dense.weight": "pytorch_model-00026-of-00036.bin",
569
+ "transformer.h.50.self_attention.query_key_value.bias": "pytorch_model-00026-of-00036.bin",
570
+ "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00026-of-00036.bin",
571
+ "transformer.h.51.input_layernorm.bias": "pytorch_model-00027-of-00036.bin",
572
+ "transformer.h.51.input_layernorm.weight": "pytorch_model-00027-of-00036.bin",
573
+ "transformer.h.51.mlp.dense_4h_to_h.bias": "pytorch_model-00027-of-00036.bin",
574
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00036.bin",
575
+ "transformer.h.51.mlp.dense_h_to_4h.bias": "pytorch_model-00027-of-00036.bin",
576
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00036.bin",
577
+ "transformer.h.51.post_attention_layernorm.bias": "pytorch_model-00027-of-00036.bin",
578
+ "transformer.h.51.post_attention_layernorm.weight": "pytorch_model-00027-of-00036.bin",
579
+ "transformer.h.51.self_attention.dense.bias": "pytorch_model-00027-of-00036.bin",
580
+ "transformer.h.51.self_attention.dense.weight": "pytorch_model-00027-of-00036.bin",
581
+ "transformer.h.51.self_attention.query_key_value.bias": "pytorch_model-00027-of-00036.bin",
582
+ "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00027-of-00036.bin",
583
+ "transformer.h.52.input_layernorm.bias": "pytorch_model-00027-of-00036.bin",
584
+ "transformer.h.52.input_layernorm.weight": "pytorch_model-00027-of-00036.bin",
585
+ "transformer.h.52.mlp.dense_4h_to_h.bias": "pytorch_model-00028-of-00036.bin",
586
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00036.bin",
587
+ "transformer.h.52.mlp.dense_h_to_4h.bias": "pytorch_model-00028-of-00036.bin",
588
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00036.bin",
589
+ "transformer.h.52.post_attention_layernorm.bias": "pytorch_model-00027-of-00036.bin",
590
+ "transformer.h.52.post_attention_layernorm.weight": "pytorch_model-00027-of-00036.bin",
591
+ "transformer.h.52.self_attention.dense.bias": "pytorch_model-00027-of-00036.bin",
592
+ "transformer.h.52.self_attention.dense.weight": "pytorch_model-00027-of-00036.bin",
593
+ "transformer.h.52.self_attention.query_key_value.bias": "pytorch_model-00027-of-00036.bin",
594
+ "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00027-of-00036.bin",
595
+ "transformer.h.53.input_layernorm.bias": "pytorch_model-00028-of-00036.bin",
596
+ "transformer.h.53.input_layernorm.weight": "pytorch_model-00028-of-00036.bin",
597
+ "transformer.h.53.mlp.dense_4h_to_h.bias": "pytorch_model-00028-of-00036.bin",
598
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00036.bin",
599
+ "transformer.h.53.mlp.dense_h_to_4h.bias": "pytorch_model-00028-of-00036.bin",
600
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00036.bin",
601
+ "transformer.h.53.post_attention_layernorm.bias": "pytorch_model-00028-of-00036.bin",
602
+ "transformer.h.53.post_attention_layernorm.weight": "pytorch_model-00028-of-00036.bin",
603
+ "transformer.h.53.self_attention.dense.bias": "pytorch_model-00028-of-00036.bin",
604
+ "transformer.h.53.self_attention.dense.weight": "pytorch_model-00028-of-00036.bin",
605
+ "transformer.h.53.self_attention.query_key_value.bias": "pytorch_model-00028-of-00036.bin",
606
+ "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00028-of-00036.bin",
607
+ "transformer.h.54.input_layernorm.bias": "pytorch_model-00028-of-00036.bin",
608
+ "transformer.h.54.input_layernorm.weight": "pytorch_model-00028-of-00036.bin",
609
+ "transformer.h.54.mlp.dense_4h_to_h.bias": "pytorch_model-00029-of-00036.bin",
610
+ "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00036.bin",
611
+ "transformer.h.54.mlp.dense_h_to_4h.bias": "pytorch_model-00029-of-00036.bin",
612
+ "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00036.bin",
613
+ "transformer.h.54.post_attention_layernorm.bias": "pytorch_model-00028-of-00036.bin",
614
+ "transformer.h.54.post_attention_layernorm.weight": "pytorch_model-00028-of-00036.bin",
615
+ "transformer.h.54.self_attention.dense.bias": "pytorch_model-00028-of-00036.bin",
616
+ "transformer.h.54.self_attention.dense.weight": "pytorch_model-00028-of-00036.bin",
617
+ "transformer.h.54.self_attention.query_key_value.bias": "pytorch_model-00028-of-00036.bin",
618
+ "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00028-of-00036.bin",
619
+ "transformer.h.55.input_layernorm.bias": "pytorch_model-00029-of-00036.bin",
620
+ "transformer.h.55.input_layernorm.weight": "pytorch_model-00029-of-00036.bin",
621
+ "transformer.h.55.mlp.dense_4h_to_h.bias": "pytorch_model-00029-of-00036.bin",
622
+ "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00036.bin",
623
+ "transformer.h.55.mlp.dense_h_to_4h.bias": "pytorch_model-00029-of-00036.bin",
624
+ "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00036.bin",
625
+ "transformer.h.55.post_attention_layernorm.bias": "pytorch_model-00029-of-00036.bin",
626
+ "transformer.h.55.post_attention_layernorm.weight": "pytorch_model-00029-of-00036.bin",
627
+ "transformer.h.55.self_attention.dense.bias": "pytorch_model-00029-of-00036.bin",
628
+ "transformer.h.55.self_attention.dense.weight": "pytorch_model-00029-of-00036.bin",
629
+ "transformer.h.55.self_attention.query_key_value.bias": "pytorch_model-00029-of-00036.bin",
630
+ "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00029-of-00036.bin",
631
+ "transformer.h.56.input_layernorm.bias": "pytorch_model-00029-of-00036.bin",
632
+ "transformer.h.56.input_layernorm.weight": "pytorch_model-00029-of-00036.bin",
633
+ "transformer.h.56.mlp.dense_4h_to_h.bias": "pytorch_model-00030-of-00036.bin",
634
+ "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00036.bin",
635
+ "transformer.h.56.mlp.dense_h_to_4h.bias": "pytorch_model-00030-of-00036.bin",
636
+ "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00036.bin",
637
+ "transformer.h.56.post_attention_layernorm.bias": "pytorch_model-00029-of-00036.bin",
638
+ "transformer.h.56.post_attention_layernorm.weight": "pytorch_model-00029-of-00036.bin",
639
+ "transformer.h.56.self_attention.dense.bias": "pytorch_model-00029-of-00036.bin",
640
+ "transformer.h.56.self_attention.dense.weight": "pytorch_model-00029-of-00036.bin",
641
+ "transformer.h.56.self_attention.query_key_value.bias": "pytorch_model-00029-of-00036.bin",
642
+ "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00029-of-00036.bin",
643
+ "transformer.h.57.input_layernorm.bias": "pytorch_model-00030-of-00036.bin",
644
+ "transformer.h.57.input_layernorm.weight": "pytorch_model-00030-of-00036.bin",
645
+ "transformer.h.57.mlp.dense_4h_to_h.bias": "pytorch_model-00030-of-00036.bin",
646
+ "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00036.bin",
647
+ "transformer.h.57.mlp.dense_h_to_4h.bias": "pytorch_model-00030-of-00036.bin",
648
+ "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00036.bin",
649
+ "transformer.h.57.post_attention_layernorm.bias": "pytorch_model-00030-of-00036.bin",
650
+ "transformer.h.57.post_attention_layernorm.weight": "pytorch_model-00030-of-00036.bin",
651
+ "transformer.h.57.self_attention.dense.bias": "pytorch_model-00030-of-00036.bin",
652
+ "transformer.h.57.self_attention.dense.weight": "pytorch_model-00030-of-00036.bin",
653
+ "transformer.h.57.self_attention.query_key_value.bias": "pytorch_model-00030-of-00036.bin",
654
+ "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00030-of-00036.bin",
655
+ "transformer.h.58.input_layernorm.bias": "pytorch_model-00030-of-00036.bin",
656
+ "transformer.h.58.input_layernorm.weight": "pytorch_model-00030-of-00036.bin",
657
+ "transformer.h.58.mlp.dense_4h_to_h.bias": "pytorch_model-00031-of-00036.bin",
658
+ "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00036.bin",
659
+ "transformer.h.58.mlp.dense_h_to_4h.bias": "pytorch_model-00031-of-00036.bin",
660
+ "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00036.bin",
661
+ "transformer.h.58.post_attention_layernorm.bias": "pytorch_model-00030-of-00036.bin",
662
+ "transformer.h.58.post_attention_layernorm.weight": "pytorch_model-00030-of-00036.bin",
663
+ "transformer.h.58.self_attention.dense.bias": "pytorch_model-00030-of-00036.bin",
664
+ "transformer.h.58.self_attention.dense.weight": "pytorch_model-00030-of-00036.bin",
665
+ "transformer.h.58.self_attention.query_key_value.bias": "pytorch_model-00030-of-00036.bin",
666
+ "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00030-of-00036.bin",
667
+ "transformer.h.59.input_layernorm.bias": "pytorch_model-00031-of-00036.bin",
668
+ "transformer.h.59.input_layernorm.weight": "pytorch_model-00031-of-00036.bin",
669
+ "transformer.h.59.mlp.dense_4h_to_h.bias": "pytorch_model-00031-of-00036.bin",
670
+ "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00036.bin",
671
+ "transformer.h.59.mlp.dense_h_to_4h.bias": "pytorch_model-00031-of-00036.bin",
672
+ "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00036.bin",
673
+ "transformer.h.59.post_attention_layernorm.bias": "pytorch_model-00031-of-00036.bin",
674
+ "transformer.h.59.post_attention_layernorm.weight": "pytorch_model-00031-of-00036.bin",
675
+ "transformer.h.59.self_attention.dense.bias": "pytorch_model-00031-of-00036.bin",
676
+ "transformer.h.59.self_attention.dense.weight": "pytorch_model-00031-of-00036.bin",
677
+ "transformer.h.59.self_attention.query_key_value.bias": "pytorch_model-00031-of-00036.bin",
678
+ "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00031-of-00036.bin",
679
+ "transformer.h.6.input_layernorm.bias": "pytorch_model-00004-of-00036.bin",
680
+ "transformer.h.6.input_layernorm.weight": "pytorch_model-00004-of-00036.bin",
681
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00036.bin",
682
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00036.bin",
683
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00036.bin",
684
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00036.bin",
685
+ "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00036.bin",
686
+ "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00036.bin",
687
+ "transformer.h.6.self_attention.dense.bias": "pytorch_model-00004-of-00036.bin",
688
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00036.bin",
689
+ "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00004-of-00036.bin",
690
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00036.bin",
691
+ "transformer.h.60.input_layernorm.bias": "pytorch_model-00031-of-00036.bin",
692
+ "transformer.h.60.input_layernorm.weight": "pytorch_model-00031-of-00036.bin",
693
+ "transformer.h.60.mlp.dense_4h_to_h.bias": "pytorch_model-00032-of-00036.bin",
694
+ "transformer.h.60.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00036.bin",
695
+ "transformer.h.60.mlp.dense_h_to_4h.bias": "pytorch_model-00032-of-00036.bin",
696
+ "transformer.h.60.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00036.bin",
697
+ "transformer.h.60.post_attention_layernorm.bias": "pytorch_model-00031-of-00036.bin",
698
+ "transformer.h.60.post_attention_layernorm.weight": "pytorch_model-00031-of-00036.bin",
699
+ "transformer.h.60.self_attention.dense.bias": "pytorch_model-00031-of-00036.bin",
700
+ "transformer.h.60.self_attention.dense.weight": "pytorch_model-00031-of-00036.bin",
701
+ "transformer.h.60.self_attention.query_key_value.bias": "pytorch_model-00031-of-00036.bin",
702
+ "transformer.h.60.self_attention.query_key_value.weight": "pytorch_model-00031-of-00036.bin",
703
+ "transformer.h.61.input_layernorm.bias": "pytorch_model-00032-of-00036.bin",
704
+ "transformer.h.61.input_layernorm.weight": "pytorch_model-00032-of-00036.bin",
705
+ "transformer.h.61.mlp.dense_4h_to_h.bias": "pytorch_model-00032-of-00036.bin",
706
+ "transformer.h.61.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00036.bin",
707
+ "transformer.h.61.mlp.dense_h_to_4h.bias": "pytorch_model-00032-of-00036.bin",
708
+ "transformer.h.61.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00036.bin",
709
+ "transformer.h.61.post_attention_layernorm.bias": "pytorch_model-00032-of-00036.bin",
710
+ "transformer.h.61.post_attention_layernorm.weight": "pytorch_model-00032-of-00036.bin",
711
+ "transformer.h.61.self_attention.dense.bias": "pytorch_model-00032-of-00036.bin",
712
+ "transformer.h.61.self_attention.dense.weight": "pytorch_model-00032-of-00036.bin",
713
+ "transformer.h.61.self_attention.query_key_value.bias": "pytorch_model-00032-of-00036.bin",
714
+ "transformer.h.61.self_attention.query_key_value.weight": "pytorch_model-00032-of-00036.bin",
715
+ "transformer.h.62.input_layernorm.bias": "pytorch_model-00032-of-00036.bin",
716
+ "transformer.h.62.input_layernorm.weight": "pytorch_model-00032-of-00036.bin",
717
+ "transformer.h.62.mlp.dense_4h_to_h.bias": "pytorch_model-00033-of-00036.bin",
718
+ "transformer.h.62.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00036.bin",
719
+ "transformer.h.62.mlp.dense_h_to_4h.bias": "pytorch_model-00033-of-00036.bin",
720
+ "transformer.h.62.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00036.bin",
721
+ "transformer.h.62.post_attention_layernorm.bias": "pytorch_model-00032-of-00036.bin",
722
+ "transformer.h.62.post_attention_layernorm.weight": "pytorch_model-00032-of-00036.bin",
723
+ "transformer.h.62.self_attention.dense.bias": "pytorch_model-00032-of-00036.bin",
724
+ "transformer.h.62.self_attention.dense.weight": "pytorch_model-00032-of-00036.bin",
725
+ "transformer.h.62.self_attention.query_key_value.bias": "pytorch_model-00032-of-00036.bin",
726
+ "transformer.h.62.self_attention.query_key_value.weight": "pytorch_model-00032-of-00036.bin",
727
+ "transformer.h.63.input_layernorm.bias": "pytorch_model-00033-of-00036.bin",
728
+ "transformer.h.63.input_layernorm.weight": "pytorch_model-00033-of-00036.bin",
729
+ "transformer.h.63.mlp.dense_4h_to_h.bias": "pytorch_model-00033-of-00036.bin",
730
+ "transformer.h.63.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00036.bin",
731
+ "transformer.h.63.mlp.dense_h_to_4h.bias": "pytorch_model-00033-of-00036.bin",
732
+ "transformer.h.63.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00036.bin",
733
+ "transformer.h.63.post_attention_layernorm.bias": "pytorch_model-00033-of-00036.bin",
734
+ "transformer.h.63.post_attention_layernorm.weight": "pytorch_model-00033-of-00036.bin",
735
+ "transformer.h.63.self_attention.dense.bias": "pytorch_model-00033-of-00036.bin",
736
+ "transformer.h.63.self_attention.dense.weight": "pytorch_model-00033-of-00036.bin",
737
+ "transformer.h.63.self_attention.query_key_value.bias": "pytorch_model-00033-of-00036.bin",
738
+ "transformer.h.63.self_attention.query_key_value.weight": "pytorch_model-00033-of-00036.bin",
739
+ "transformer.h.64.input_layernorm.bias": "pytorch_model-00033-of-00036.bin",
740
+ "transformer.h.64.input_layernorm.weight": "pytorch_model-00033-of-00036.bin",
741
+ "transformer.h.64.mlp.dense_4h_to_h.bias": "pytorch_model-00034-of-00036.bin",
742
+ "transformer.h.64.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00036.bin",
743
+ "transformer.h.64.mlp.dense_h_to_4h.bias": "pytorch_model-00034-of-00036.bin",
744
+ "transformer.h.64.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00036.bin",
745
+ "transformer.h.64.post_attention_layernorm.bias": "pytorch_model-00033-of-00036.bin",
746
+ "transformer.h.64.post_attention_layernorm.weight": "pytorch_model-00033-of-00036.bin",
747
+ "transformer.h.64.self_attention.dense.bias": "pytorch_model-00033-of-00036.bin",
748
+ "transformer.h.64.self_attention.dense.weight": "pytorch_model-00033-of-00036.bin",
749
+ "transformer.h.64.self_attention.query_key_value.bias": "pytorch_model-00033-of-00036.bin",
750
+ "transformer.h.64.self_attention.query_key_value.weight": "pytorch_model-00033-of-00036.bin",
751
+ "transformer.h.65.input_layernorm.bias": "pytorch_model-00034-of-00036.bin",
752
+ "transformer.h.65.input_layernorm.weight": "pytorch_model-00034-of-00036.bin",
753
+ "transformer.h.65.mlp.dense_4h_to_h.bias": "pytorch_model-00034-of-00036.bin",
754
+ "transformer.h.65.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00036.bin",
755
+ "transformer.h.65.mlp.dense_h_to_4h.bias": "pytorch_model-00034-of-00036.bin",
756
+ "transformer.h.65.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00036.bin",
757
+ "transformer.h.65.post_attention_layernorm.bias": "pytorch_model-00034-of-00036.bin",
758
+ "transformer.h.65.post_attention_layernorm.weight": "pytorch_model-00034-of-00036.bin",
759
+ "transformer.h.65.self_attention.dense.bias": "pytorch_model-00034-of-00036.bin",
760
+ "transformer.h.65.self_attention.dense.weight": "pytorch_model-00034-of-00036.bin",
761
+ "transformer.h.65.self_attention.query_key_value.bias": "pytorch_model-00034-of-00036.bin",
762
+ "transformer.h.65.self_attention.query_key_value.weight": "pytorch_model-00034-of-00036.bin",
763
+ "transformer.h.66.input_layernorm.bias": "pytorch_model-00034-of-00036.bin",
764
+ "transformer.h.66.input_layernorm.weight": "pytorch_model-00034-of-00036.bin",
765
+ "transformer.h.66.mlp.dense_4h_to_h.bias": "pytorch_model-00035-of-00036.bin",
766
+ "transformer.h.66.mlp.dense_4h_to_h.weight": "pytorch_model-00035-of-00036.bin",
767
+ "transformer.h.66.mlp.dense_h_to_4h.bias": "pytorch_model-00035-of-00036.bin",
768
+ "transformer.h.66.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00036.bin",
769
+ "transformer.h.66.post_attention_layernorm.bias": "pytorch_model-00034-of-00036.bin",
770
+ "transformer.h.66.post_attention_layernorm.weight": "pytorch_model-00034-of-00036.bin",
771
+ "transformer.h.66.self_attention.dense.bias": "pytorch_model-00034-of-00036.bin",
772
+ "transformer.h.66.self_attention.dense.weight": "pytorch_model-00034-of-00036.bin",
773
+ "transformer.h.66.self_attention.query_key_value.bias": "pytorch_model-00034-of-00036.bin",
774
+ "transformer.h.66.self_attention.query_key_value.weight": "pytorch_model-00034-of-00036.bin",
775
+ "transformer.h.67.input_layernorm.bias": "pytorch_model-00035-of-00036.bin",
776
+ "transformer.h.67.input_layernorm.weight": "pytorch_model-00035-of-00036.bin",
777
+ "transformer.h.67.mlp.dense_4h_to_h.bias": "pytorch_model-00035-of-00036.bin",
778
+ "transformer.h.67.mlp.dense_4h_to_h.weight": "pytorch_model-00035-of-00036.bin",
779
+ "transformer.h.67.mlp.dense_h_to_4h.bias": "pytorch_model-00035-of-00036.bin",
780
+ "transformer.h.67.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00036.bin",
781
+ "transformer.h.67.post_attention_layernorm.bias": "pytorch_model-00035-of-00036.bin",
782
+ "transformer.h.67.post_attention_layernorm.weight": "pytorch_model-00035-of-00036.bin",
783
+ "transformer.h.67.self_attention.dense.bias": "pytorch_model-00035-of-00036.bin",
784
+ "transformer.h.67.self_attention.dense.weight": "pytorch_model-00035-of-00036.bin",
785
+ "transformer.h.67.self_attention.query_key_value.bias": "pytorch_model-00035-of-00036.bin",
786
+ "transformer.h.67.self_attention.query_key_value.weight": "pytorch_model-00035-of-00036.bin",
787
+ "transformer.h.68.input_layernorm.bias": "pytorch_model-00035-of-00036.bin",
788
+ "transformer.h.68.input_layernorm.weight": "pytorch_model-00035-of-00036.bin",
789
+ "transformer.h.68.mlp.dense_4h_to_h.bias": "pytorch_model-00036-of-00036.bin",
790
+ "transformer.h.68.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00036.bin",
791
+ "transformer.h.68.mlp.dense_h_to_4h.bias": "pytorch_model-00036-of-00036.bin",
792
+ "transformer.h.68.mlp.dense_h_to_4h.weight": "pytorch_model-00036-of-00036.bin",
793
+ "transformer.h.68.post_attention_layernorm.bias": "pytorch_model-00035-of-00036.bin",
794
+ "transformer.h.68.post_attention_layernorm.weight": "pytorch_model-00035-of-00036.bin",
795
+ "transformer.h.68.self_attention.dense.bias": "pytorch_model-00035-of-00036.bin",
796
+ "transformer.h.68.self_attention.dense.weight": "pytorch_model-00035-of-00036.bin",
797
+ "transformer.h.68.self_attention.query_key_value.bias": "pytorch_model-00035-of-00036.bin",
798
+ "transformer.h.68.self_attention.query_key_value.weight": "pytorch_model-00035-of-00036.bin",
799
+ "transformer.h.69.input_layernorm.bias": "pytorch_model-00036-of-00036.bin",
800
+ "transformer.h.69.input_layernorm.weight": "pytorch_model-00036-of-00036.bin",
801
+ "transformer.h.69.mlp.dense_4h_to_h.bias": "pytorch_model-00036-of-00036.bin",
802
+ "transformer.h.69.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00036.bin",
803
+ "transformer.h.69.mlp.dense_h_to_4h.bias": "pytorch_model-00036-of-00036.bin",
804
+ "transformer.h.69.mlp.dense_h_to_4h.weight": "pytorch_model-00036-of-00036.bin",
805
+ "transformer.h.69.post_attention_layernorm.bias": "pytorch_model-00036-of-00036.bin",
806
+ "transformer.h.69.post_attention_layernorm.weight": "pytorch_model-00036-of-00036.bin",
807
+ "transformer.h.69.self_attention.dense.bias": "pytorch_model-00036-of-00036.bin",
808
+ "transformer.h.69.self_attention.dense.weight": "pytorch_model-00036-of-00036.bin",
809
+ "transformer.h.69.self_attention.query_key_value.bias": "pytorch_model-00036-of-00036.bin",
810
+ "transformer.h.69.self_attention.query_key_value.weight": "pytorch_model-00036-of-00036.bin",
811
+ "transformer.h.7.input_layernorm.bias": "pytorch_model-00005-of-00036.bin",
812
+ "transformer.h.7.input_layernorm.weight": "pytorch_model-00005-of-00036.bin",
813
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00036.bin",
814
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00036.bin",
815
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00036.bin",
816
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00036.bin",
817
+ "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00005-of-00036.bin",
818
+ "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00036.bin",
819
+ "transformer.h.7.self_attention.dense.bias": "pytorch_model-00005-of-00036.bin",
820
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00005-of-00036.bin",
821
+ "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00005-of-00036.bin",
822
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00005-of-00036.bin",
823
+ "transformer.h.8.input_layernorm.bias": "pytorch_model-00005-of-00036.bin",
824
+ "transformer.h.8.input_layernorm.weight": "pytorch_model-00005-of-00036.bin",
825
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00036.bin",
826
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00036.bin",
827
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00036.bin",
828
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00036.bin",
829
+ "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00005-of-00036.bin",
830
+ "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00036.bin",
831
+ "transformer.h.8.self_attention.dense.bias": "pytorch_model-00005-of-00036.bin",
832
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00005-of-00036.bin",
833
+ "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00005-of-00036.bin",
834
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00005-of-00036.bin",
835
+ "transformer.h.9.input_layernorm.bias": "pytorch_model-00006-of-00036.bin",
836
+ "transformer.h.9.input_layernorm.weight": "pytorch_model-00006-of-00036.bin",
837
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00036.bin",
838
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00036.bin",
839
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00036.bin",
840
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00036.bin",
841
+ "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00006-of-00036.bin",
842
+ "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00036.bin",
843
+ "transformer.h.9.self_attention.dense.bias": "pytorch_model-00006-of-00036.bin",
844
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00006-of-00036.bin",
845
+ "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00006-of-00036.bin",
846
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00006-of-00036.bin",
847
+ "transformer.ln_f.bias": "pytorch_model-00036-of-00036.bin",
848
+ "transformer.ln_f.weight": "pytorch_model-00036-of-00036.bin",
849
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00036.bin",
850
+ "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00036.bin",
851
+ "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00036.bin"
852
+ }
853
+ }