Hugging Face's logo

sboughorbel
/
bloomz-8bit

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Inference Endpoints
8-bit precision
Model card Files Community
sboughorbel commited on
Commit
d7993a3
•
1 Parent(s): 36456b6

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. config.json +33 -0
  3. generation_config.json +7 -0
  4. pytorch_model-00001-of-00019.bin +3 -0
  5. pytorch_model-00002-of-00019.bin +3 -0
  6. pytorch_model-00003-of-00019.bin +3 -0
  7. pytorch_model-00004-of-00019.bin +3 -0
  8. pytorch_model-00005-of-00019.bin +3 -0
  9. pytorch_model-00006-of-00019.bin +3 -0
  10. pytorch_model-00007-of-00019.bin +3 -0
  11. pytorch_model-00008-of-00019.bin +3 -0
  12. pytorch_model-00009-of-00019.bin +3 -0
  13. pytorch_model-00010-of-00019.bin +3 -0
  14. pytorch_model-00011-of-00019.bin +3 -0
  15. pytorch_model-00012-of-00019.bin +3 -0
  16. pytorch_model-00013-of-00019.bin +3 -0
  17. pytorch_model-00014-of-00019.bin +3 -0
  18. pytorch_model-00015-of-00019.bin +3 -0
  19. pytorch_model-00016-of-00019.bin +3 -0
  20. pytorch_model-00017-of-00019.bin +3 -0
  21. pytorch_model-00018-of-00019.bin +3 -0
  22. pytorch_model-00019-of-00019.bin +3 -0
  23. pytorch_model.bin.index.json +1133 -0
  24. special_tokens_map.json +6 -0
  25. tokenizer.json +3 -0
  26. tokenizer_config.json +11 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/export/work/sboughorbel/bloomz/",
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
+ "quantization_config": {
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_skip_modules": null,
24
+ "llm_int8_threshold": 6.0,
25
+ "load_in_8bit": true
26
+ },
27
+ "seq_length": 2048,
28
+ "slow_but_exact": false,
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.28.0",
31
+ "use_cache": true,
32
+ "vocab_size": 250880
33
+ }
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": "4.28.0"
7
+ }
pytorch_model-00001-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d0cc652cacedd96b31dc05dd9bf591be6cdba0a945dbefc167db3487bbbcf3
3
+ size 9660493345
pytorch_model-00002-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f387425894712a41442ba23360319edc555ae396caa98344fe3c8e27d4309a
3
+ size 9868581151
pytorch_model-00003-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a08e8dd73e366e29757a87effa8a5aa3937c75cb78f2b37d6545b91727e31a
3
+ size 9868581151
pytorch_model-00004-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3baf81ac60c10a4f8f1216ac04a497509654adbb0a52ec9bfa34ace04c4bde
3
+ size 9868581215
pytorch_model-00005-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f15a5cea947940541550232ea0c202bbd0280305fd33a0fcf476c5687e29f08
3
+ size 9868581215
pytorch_model-00006-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf94245e419c322f7951322e900c6440852c72913a8bf49ddb9a1f8f2d5e061
3
+ size 9868581215
pytorch_model-00007-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e253d8e2ce819e0aba8d9b7be1d0210fcd9ed7dc473c89fcd94d356abc25466d
3
+ size 9868581215
pytorch_model-00008-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c376582bf53b467130322beb78e3c18a8011b970888129fa39230557e87b4ac5
3
+ size 9868581215
pytorch_model-00009-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dc066614f540fb6137ea99c34cc4fdad2904290516e448cba94207edebebcb
3
+ size 9868581215
pytorch_model-00010-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e377971de411ebb407f1acf5f481a0067f67f5d9025981081f9d4bd36cf415cd
3
+ size 9868581215
pytorch_model-00011-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df23b0333b1e07767107f60b18934ae9d53d4e643170c2dbc73e890c9e58b1e0
3
+ size 9868581215
pytorch_model-00012-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72878b59f2fc1dc5361794ccc4123c64544797b45b1fb451c56ef1cc5049819c
3
+ size 9868581215
pytorch_model-00013-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f997051137a336fc2deae2d6d8408a90a6ce1bdba53834573047579e2096095
3
+ size 9868581215
pytorch_model-00014-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269f16dcb128616f0643f459edeac3a83e2672bb6923f9a447dc515e5477c279
3
+ size 9868581215
pytorch_model-00015-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c84b5d8125e2868f5a5437a3727705693789f81ac32a36289462d9d9c627cb
3
+ size 9868581215
pytorch_model-00016-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a0effab5b4f3f99f07af7c63ec39eabf9d47119e358dfdde2c69c7690edcb2
3
+ size 9868581215
pytorch_model-00017-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad8b1ae43237d3c8a77d038fb3743d6c1d01a39a7b3bd812e543a55b5747a93
3
+ size 9868581215
pytorch_model-00018-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37b8ecfacf5eba4a155d3cd17c9c4d5b30970efc1c25fbf7a21c965efe3d1e5
3
+ size 9868581215
pytorch_model-00019-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81af1dbe3e121078e0b7a6e8d18a81187857285feda429c08ae4c8b37232e84
3
+ size 9660377225
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 187086348288
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00019-of-00019.bin",
7
+ "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00019.bin",
8
+ "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00019.bin",
9
+ "transformer.h.0.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00019.bin",
10
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00019.bin",
11
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00019.bin",
12
+ "transformer.h.0.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00019.bin",
13
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00019.bin",
14
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00019.bin",
15
+ "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00019.bin",
16
+ "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00019.bin",
17
+ "transformer.h.0.self_attention.dense.SCB": "pytorch_model-00001-of-00019.bin",
18
+ "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00019.bin",
19
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00019.bin",
20
+ "transformer.h.0.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00019.bin",
21
+ "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00019.bin",
22
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00019.bin",
23
+ "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00019.bin",
24
+ "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00019.bin",
25
+ "transformer.h.1.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00019.bin",
26
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00019.bin",
27
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00019.bin",
28
+ "transformer.h.1.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00019.bin",
29
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00019.bin",
30
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00019.bin",
31
+ "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00019.bin",
32
+ "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
33
+ "transformer.h.1.self_attention.dense.SCB": "pytorch_model-00002-of-00019.bin",
34
+ "transformer.h.1.self_attention.dense.bias": "pytorch_model-00002-of-00019.bin",
35
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00002-of-00019.bin",
36
+ "transformer.h.1.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00019.bin",
37
+ "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00002-of-00019.bin",
38
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00002-of-00019.bin",
39
+ "transformer.h.10.input_layernorm.bias": "pytorch_model-00004-of-00019.bin",
40
+ "transformer.h.10.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
41
+ "transformer.h.10.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00019.bin",
42
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00019.bin",
43
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00019.bin",
44
+ "transformer.h.10.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00019.bin",
45
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00019.bin",
46
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00019.bin",
47
+ "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00019.bin",
48
+ "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
49
+ "transformer.h.10.self_attention.dense.SCB": "pytorch_model-00004-of-00019.bin",
50
+ "transformer.h.10.self_attention.dense.bias": "pytorch_model-00004-of-00019.bin",
51
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00004-of-00019.bin",
52
+ "transformer.h.10.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00019.bin",
53
+ "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00004-of-00019.bin",
54
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00004-of-00019.bin",
55
+ "transformer.h.11.input_layernorm.bias": "pytorch_model-00004-of-00019.bin",
56
+ "transformer.h.11.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
57
+ "transformer.h.11.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00019.bin",
58
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00019.bin",
59
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00019.bin",
60
+ "transformer.h.11.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00019.bin",
61
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00019.bin",
62
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00019.bin",
63
+ "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00019.bin",
64
+ "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
65
+ "transformer.h.11.self_attention.dense.SCB": "pytorch_model-00004-of-00019.bin",
66
+ "transformer.h.11.self_attention.dense.bias": "pytorch_model-00004-of-00019.bin",
67
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00004-of-00019.bin",
68
+ "transformer.h.11.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00019.bin",
69
+ "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00004-of-00019.bin",
70
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00004-of-00019.bin",
71
+ "transformer.h.12.input_layernorm.bias": "pytorch_model-00004-of-00019.bin",
72
+ "transformer.h.12.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
73
+ "transformer.h.12.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00019.bin",
74
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00019.bin",
75
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00019.bin",
76
+ "transformer.h.12.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00019.bin",
77
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00019.bin",
78
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00019.bin",
79
+ "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00019.bin",
80
+ "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
81
+ "transformer.h.12.self_attention.dense.SCB": "pytorch_model-00004-of-00019.bin",
82
+ "transformer.h.12.self_attention.dense.bias": "pytorch_model-00004-of-00019.bin",
83
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00004-of-00019.bin",
84
+ "transformer.h.12.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00019.bin",
85
+ "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00004-of-00019.bin",
86
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00004-of-00019.bin",
87
+ "transformer.h.13.input_layernorm.bias": "pytorch_model-00004-of-00019.bin",
88
+ "transformer.h.13.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
89
+ "transformer.h.13.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00019.bin",
90
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00019.bin",
91
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00019.bin",
92
+ "transformer.h.13.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00019.bin",
93
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00019.bin",
94
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00019.bin",
95
+ "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00005-of-00019.bin",
96
+ "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
97
+ "transformer.h.13.self_attention.dense.SCB": "pytorch_model-00005-of-00019.bin",
98
+ "transformer.h.13.self_attention.dense.bias": "pytorch_model-00005-of-00019.bin",
99
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00005-of-00019.bin",
100
+ "transformer.h.13.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00019.bin",
101
+ "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00005-of-00019.bin",
102
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00005-of-00019.bin",
103
+ "transformer.h.14.input_layernorm.bias": "pytorch_model-00005-of-00019.bin",
104
+ "transformer.h.14.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
105
+ "transformer.h.14.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00019.bin",
106
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00019.bin",
107
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00019.bin",
108
+ "transformer.h.14.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00019.bin",
109
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00019.bin",
110
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00019.bin",
111
+ "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00005-of-00019.bin",
112
+ "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
113
+ "transformer.h.14.self_attention.dense.SCB": "pytorch_model-00005-of-00019.bin",
114
+ "transformer.h.14.self_attention.dense.bias": "pytorch_model-00005-of-00019.bin",
115
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00005-of-00019.bin",
116
+ "transformer.h.14.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00019.bin",
117
+ "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00005-of-00019.bin",
118
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00005-of-00019.bin",
119
+ "transformer.h.15.input_layernorm.bias": "pytorch_model-00005-of-00019.bin",
120
+ "transformer.h.15.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
121
+ "transformer.h.15.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00019.bin",
122
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00019.bin",
123
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00019.bin",
124
+ "transformer.h.15.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00019.bin",
125
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00019.bin",
126
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00019.bin",
127
+ "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00005-of-00019.bin",
128
+ "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
129
+ "transformer.h.15.self_attention.dense.SCB": "pytorch_model-00005-of-00019.bin",
130
+ "transformer.h.15.self_attention.dense.bias": "pytorch_model-00005-of-00019.bin",
131
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00005-of-00019.bin",
132
+ "transformer.h.15.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00019.bin",
133
+ "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00005-of-00019.bin",
134
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00005-of-00019.bin",
135
+ "transformer.h.16.input_layernorm.bias": "pytorch_model-00005-of-00019.bin",
136
+ "transformer.h.16.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
137
+ "transformer.h.16.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00019.bin",
138
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00019.bin",
139
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00019.bin",
140
+ "transformer.h.16.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00019.bin",
141
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00019.bin",
142
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00019.bin",
143
+ "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00005-of-00019.bin",
144
+ "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
145
+ "transformer.h.16.self_attention.dense.SCB": "pytorch_model-00005-of-00019.bin",
146
+ "transformer.h.16.self_attention.dense.bias": "pytorch_model-00005-of-00019.bin",
147
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00005-of-00019.bin",
148
+ "transformer.h.16.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00019.bin",
149
+ "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00005-of-00019.bin",
150
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00005-of-00019.bin",
151
+ "transformer.h.17.input_layernorm.bias": "pytorch_model-00005-of-00019.bin",
152
+ "transformer.h.17.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
153
+ "transformer.h.17.mlp.dense_4h_to_h.SCB": "pytorch_model-00006-of-00019.bin",
154
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00019.bin",
155
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00019.bin",
156
+ "transformer.h.17.mlp.dense_h_to_4h.SCB": "pytorch_model-00006-of-00019.bin",
157
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00019.bin",
158
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00019.bin",
159
+ "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00006-of-00019.bin",
160
+ "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
161
+ "transformer.h.17.self_attention.dense.SCB": "pytorch_model-00006-of-00019.bin",
162
+ "transformer.h.17.self_attention.dense.bias": "pytorch_model-00006-of-00019.bin",
163
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00006-of-00019.bin",
164
+ "transformer.h.17.self_attention.query_key_value.SCB": "pytorch_model-00006-of-00019.bin",
165
+ "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00006-of-00019.bin",
166
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00006-of-00019.bin",
167
+ "transformer.h.18.input_layernorm.bias": "pytorch_model-00006-of-00019.bin",
168
+ "transformer.h.18.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
169
+ "transformer.h.18.mlp.dense_4h_to_h.SCB": "pytorch_model-00006-of-00019.bin",
170
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00019.bin",
171
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00019.bin",
172
+ "transformer.h.18.mlp.dense_h_to_4h.SCB": "pytorch_model-00006-of-00019.bin",
173
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00019.bin",
174
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00019.bin",
175
+ "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00006-of-00019.bin",
176
+ "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
177
+ "transformer.h.18.self_attention.dense.SCB": "pytorch_model-00006-of-00019.bin",
178
+ "transformer.h.18.self_attention.dense.bias": "pytorch_model-00006-of-00019.bin",
179
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00006-of-00019.bin",
180
+ "transformer.h.18.self_attention.query_key_value.SCB": "pytorch_model-00006-of-00019.bin",
181
+ "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00006-of-00019.bin",
182
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00006-of-00019.bin",
183
+ "transformer.h.19.input_layernorm.bias": "pytorch_model-00006-of-00019.bin",
184
+ "transformer.h.19.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
185
+ "transformer.h.19.mlp.dense_4h_to_h.SCB": "pytorch_model-00006-of-00019.bin",
186
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00019.bin",
187
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00019.bin",
188
+ "transformer.h.19.mlp.dense_h_to_4h.SCB": "pytorch_model-00006-of-00019.bin",
189
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00019.bin",
190
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00019.bin",
191
+ "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00006-of-00019.bin",
192
+ "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
193
+ "transformer.h.19.self_attention.dense.SCB": "pytorch_model-00006-of-00019.bin",
194
+ "transformer.h.19.self_attention.dense.bias": "pytorch_model-00006-of-00019.bin",
195
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00006-of-00019.bin",
196
+ "transformer.h.19.self_attention.query_key_value.SCB": "pytorch_model-00006-of-00019.bin",
197
+ "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00006-of-00019.bin",
198
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00006-of-00019.bin",
199
+ "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00019.bin",
200
+ "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
201
+ "transformer.h.2.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00019.bin",
202
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00019.bin",
203
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00019.bin",
204
+ "transformer.h.2.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00019.bin",
205
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00019.bin",
206
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00019.bin",
207
+ "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00019.bin",
208
+ "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
209
+ "transformer.h.2.self_attention.dense.SCB": "pytorch_model-00002-of-00019.bin",
210
+ "transformer.h.2.self_attention.dense.bias": "pytorch_model-00002-of-00019.bin",
211
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00019.bin",
212
+ "transformer.h.2.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00019.bin",
213
+ "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00019.bin",
214
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00019.bin",
215
+ "transformer.h.20.input_layernorm.bias": "pytorch_model-00006-of-00019.bin",
216
+ "transformer.h.20.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
217
+ "transformer.h.20.mlp.dense_4h_to_h.SCB": "pytorch_model-00006-of-00019.bin",
218
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00019.bin",
219
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00019.bin",
220
+ "transformer.h.20.mlp.dense_h_to_4h.SCB": "pytorch_model-00006-of-00019.bin",
221
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00019.bin",
222
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00019.bin",
223
+ "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00006-of-00019.bin",
224
+ "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
225
+ "transformer.h.20.self_attention.dense.SCB": "pytorch_model-00006-of-00019.bin",
226
+ "transformer.h.20.self_attention.dense.bias": "pytorch_model-00006-of-00019.bin",
227
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00006-of-00019.bin",
228
+ "transformer.h.20.self_attention.query_key_value.SCB": "pytorch_model-00006-of-00019.bin",
229
+ "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00006-of-00019.bin",
230
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00006-of-00019.bin",
231
+ "transformer.h.21.input_layernorm.bias": "pytorch_model-00006-of-00019.bin",
232
+ "transformer.h.21.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
233
+ "transformer.h.21.mlp.dense_4h_to_h.SCB": "pytorch_model-00007-of-00019.bin",
234
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00019.bin",
235
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00019.bin",
236
+ "transformer.h.21.mlp.dense_h_to_4h.SCB": "pytorch_model-00007-of-00019.bin",
237
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00019.bin",
238
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00019.bin",
239
+ "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00007-of-00019.bin",
240
+ "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
241
+ "transformer.h.21.self_attention.dense.SCB": "pytorch_model-00007-of-00019.bin",
242
+ "transformer.h.21.self_attention.dense.bias": "pytorch_model-00007-of-00019.bin",
243
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00007-of-00019.bin",
244
+ "transformer.h.21.self_attention.query_key_value.SCB": "pytorch_model-00007-of-00019.bin",
245
+ "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00007-of-00019.bin",
246
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00007-of-00019.bin",
247
+ "transformer.h.22.input_layernorm.bias": "pytorch_model-00007-of-00019.bin",
248
+ "transformer.h.22.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
249
+ "transformer.h.22.mlp.dense_4h_to_h.SCB": "pytorch_model-00007-of-00019.bin",
250
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00019.bin",
251
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00019.bin",
252
+ "transformer.h.22.mlp.dense_h_to_4h.SCB": "pytorch_model-00007-of-00019.bin",
253
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00019.bin",
254
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00019.bin",
255
+ "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00007-of-00019.bin",
256
+ "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
257
+ "transformer.h.22.self_attention.dense.SCB": "pytorch_model-00007-of-00019.bin",
258
+ "transformer.h.22.self_attention.dense.bias": "pytorch_model-00007-of-00019.bin",
259
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00007-of-00019.bin",
260
+ "transformer.h.22.self_attention.query_key_value.SCB": "pytorch_model-00007-of-00019.bin",
261
+ "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00007-of-00019.bin",
262
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00007-of-00019.bin",
263
+ "transformer.h.23.input_layernorm.bias": "pytorch_model-00007-of-00019.bin",
264
+ "transformer.h.23.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
265
+ "transformer.h.23.mlp.dense_4h_to_h.SCB": "pytorch_model-00007-of-00019.bin",
266
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00019.bin",
267
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00019.bin",
268
+ "transformer.h.23.mlp.dense_h_to_4h.SCB": "pytorch_model-00007-of-00019.bin",
269
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00019.bin",
270
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00019.bin",
271
+ "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00007-of-00019.bin",
272
+ "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
273
+ "transformer.h.23.self_attention.dense.SCB": "pytorch_model-00007-of-00019.bin",
274
+ "transformer.h.23.self_attention.dense.bias": "pytorch_model-00007-of-00019.bin",
275
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00007-of-00019.bin",
276
+ "transformer.h.23.self_attention.query_key_value.SCB": "pytorch_model-00007-of-00019.bin",
277
+ "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00007-of-00019.bin",
278
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00007-of-00019.bin",
279
+ "transformer.h.24.input_layernorm.bias": "pytorch_model-00007-of-00019.bin",
280
+ "transformer.h.24.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
281
+ "transformer.h.24.mlp.dense_4h_to_h.SCB": "pytorch_model-00007-of-00019.bin",
282
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00019.bin",
283
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00019.bin",
284
+ "transformer.h.24.mlp.dense_h_to_4h.SCB": "pytorch_model-00007-of-00019.bin",
285
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00019.bin",
286
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00019.bin",
287
+ "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00007-of-00019.bin",
288
+ "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
289
+ "transformer.h.24.self_attention.dense.SCB": "pytorch_model-00007-of-00019.bin",
290
+ "transformer.h.24.self_attention.dense.bias": "pytorch_model-00007-of-00019.bin",
291
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00007-of-00019.bin",
292
+ "transformer.h.24.self_attention.query_key_value.SCB": "pytorch_model-00007-of-00019.bin",
293
+ "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00007-of-00019.bin",
294
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00007-of-00019.bin",
295
+ "transformer.h.25.input_layernorm.bias": "pytorch_model-00007-of-00019.bin",
296
+ "transformer.h.25.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
297
+ "transformer.h.25.mlp.dense_4h_to_h.SCB": "pytorch_model-00008-of-00019.bin",
298
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00019.bin",
299
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00019.bin",
300
+ "transformer.h.25.mlp.dense_h_to_4h.SCB": "pytorch_model-00008-of-00019.bin",
301
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00019.bin",
302
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00019.bin",
303
+ "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00008-of-00019.bin",
304
+ "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
305
+ "transformer.h.25.self_attention.dense.SCB": "pytorch_model-00008-of-00019.bin",
306
+ "transformer.h.25.self_attention.dense.bias": "pytorch_model-00008-of-00019.bin",
307
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00008-of-00019.bin",
308
+ "transformer.h.25.self_attention.query_key_value.SCB": "pytorch_model-00008-of-00019.bin",
309
+ "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00008-of-00019.bin",
310
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00008-of-00019.bin",
311
+ "transformer.h.26.input_layernorm.bias": "pytorch_model-00008-of-00019.bin",
312
+ "transformer.h.26.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
313
+ "transformer.h.26.mlp.dense_4h_to_h.SCB": "pytorch_model-00008-of-00019.bin",
314
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00019.bin",
315
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00019.bin",
316
+ "transformer.h.26.mlp.dense_h_to_4h.SCB": "pytorch_model-00008-of-00019.bin",
317
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00019.bin",
318
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00019.bin",
319
+ "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00008-of-00019.bin",
320
+ "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
321
+ "transformer.h.26.self_attention.dense.SCB": "pytorch_model-00008-of-00019.bin",
322
+ "transformer.h.26.self_attention.dense.bias": "pytorch_model-00008-of-00019.bin",
323
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00008-of-00019.bin",
324
+ "transformer.h.26.self_attention.query_key_value.SCB": "pytorch_model-00008-of-00019.bin",
325
+ "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00008-of-00019.bin",
326
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00008-of-00019.bin",
327
+ "transformer.h.27.input_layernorm.bias": "pytorch_model-00008-of-00019.bin",
328
+ "transformer.h.27.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
329
+ "transformer.h.27.mlp.dense_4h_to_h.SCB": "pytorch_model-00008-of-00019.bin",
330
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00019.bin",
331
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00019.bin",
332
+ "transformer.h.27.mlp.dense_h_to_4h.SCB": "pytorch_model-00008-of-00019.bin",
333
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00019.bin",
334
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00019.bin",
335
+ "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00008-of-00019.bin",
336
+ "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
337
+ "transformer.h.27.self_attention.dense.SCB": "pytorch_model-00008-of-00019.bin",
338
+ "transformer.h.27.self_attention.dense.bias": "pytorch_model-00008-of-00019.bin",
339
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00008-of-00019.bin",
340
+ "transformer.h.27.self_attention.query_key_value.SCB": "pytorch_model-00008-of-00019.bin",
341
+ "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00008-of-00019.bin",
342
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00008-of-00019.bin",
343
+ "transformer.h.28.input_layernorm.bias": "pytorch_model-00008-of-00019.bin",
344
+ "transformer.h.28.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
345
+ "transformer.h.28.mlp.dense_4h_to_h.SCB": "pytorch_model-00008-of-00019.bin",
346
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00019.bin",
347
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00019.bin",
348
+ "transformer.h.28.mlp.dense_h_to_4h.SCB": "pytorch_model-00008-of-00019.bin",
349
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00019.bin",
350
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00019.bin",
351
+ "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00008-of-00019.bin",
352
+ "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
353
+ "transformer.h.28.self_attention.dense.SCB": "pytorch_model-00008-of-00019.bin",
354
+ "transformer.h.28.self_attention.dense.bias": "pytorch_model-00008-of-00019.bin",
355
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00008-of-00019.bin",
356
+ "transformer.h.28.self_attention.query_key_value.SCB": "pytorch_model-00008-of-00019.bin",
357
+ "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00008-of-00019.bin",
358
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00008-of-00019.bin",
359
+ "transformer.h.29.input_layernorm.bias": "pytorch_model-00008-of-00019.bin",
360
+ "transformer.h.29.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
361
+ "transformer.h.29.mlp.dense_4h_to_h.SCB": "pytorch_model-00009-of-00019.bin",
362
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00019.bin",
363
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00019.bin",
364
+ "transformer.h.29.mlp.dense_h_to_4h.SCB": "pytorch_model-00009-of-00019.bin",
365
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00019.bin",
366
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00019.bin",
367
+ "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00009-of-00019.bin",
368
+ "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
369
+ "transformer.h.29.self_attention.dense.SCB": "pytorch_model-00009-of-00019.bin",
370
+ "transformer.h.29.self_attention.dense.bias": "pytorch_model-00009-of-00019.bin",
371
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00009-of-00019.bin",
372
+ "transformer.h.29.self_attention.query_key_value.SCB": "pytorch_model-00009-of-00019.bin",
373
+ "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00009-of-00019.bin",
374
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00009-of-00019.bin",
375
+ "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00019.bin",
376
+ "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
377
+ "transformer.h.3.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00019.bin",
378
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00019.bin",
379
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00019.bin",
380
+ "transformer.h.3.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00019.bin",
381
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00019.bin",
382
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00019.bin",
383
+ "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00019.bin",
384
+ "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
385
+ "transformer.h.3.self_attention.dense.SCB": "pytorch_model-00002-of-00019.bin",
386
+ "transformer.h.3.self_attention.dense.bias": "pytorch_model-00002-of-00019.bin",
387
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00019.bin",
388
+ "transformer.h.3.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00019.bin",
389
+ "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00002-of-00019.bin",
390
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00019.bin",
391
+ "transformer.h.30.input_layernorm.bias": "pytorch_model-00009-of-00019.bin",
392
+ "transformer.h.30.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
393
+ "transformer.h.30.mlp.dense_4h_to_h.SCB": "pytorch_model-00009-of-00019.bin",
394
+ "transformer.h.30.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00019.bin",
395
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00019.bin",
396
+ "transformer.h.30.mlp.dense_h_to_4h.SCB": "pytorch_model-00009-of-00019.bin",
397
+ "transformer.h.30.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00019.bin",
398
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00019.bin",
399
+ "transformer.h.30.post_attention_layernorm.bias": "pytorch_model-00009-of-00019.bin",
400
+ "transformer.h.30.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
401
+ "transformer.h.30.self_attention.dense.SCB": "pytorch_model-00009-of-00019.bin",
402
+ "transformer.h.30.self_attention.dense.bias": "pytorch_model-00009-of-00019.bin",
403
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00009-of-00019.bin",
404
+ "transformer.h.30.self_attention.query_key_value.SCB": "pytorch_model-00009-of-00019.bin",
405
+ "transformer.h.30.self_attention.query_key_value.bias": "pytorch_model-00009-of-00019.bin",
406
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00009-of-00019.bin",
407
+ "transformer.h.31.input_layernorm.bias": "pytorch_model-00009-of-00019.bin",
408
+ "transformer.h.31.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
409
+ "transformer.h.31.mlp.dense_4h_to_h.SCB": "pytorch_model-00009-of-00019.bin",
410
+ "transformer.h.31.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00019.bin",
411
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00019.bin",
412
+ "transformer.h.31.mlp.dense_h_to_4h.SCB": "pytorch_model-00009-of-00019.bin",
413
+ "transformer.h.31.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00019.bin",
414
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00019.bin",
415
+ "transformer.h.31.post_attention_layernorm.bias": "pytorch_model-00009-of-00019.bin",
416
+ "transformer.h.31.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
417
+ "transformer.h.31.self_attention.dense.SCB": "pytorch_model-00009-of-00019.bin",
418
+ "transformer.h.31.self_attention.dense.bias": "pytorch_model-00009-of-00019.bin",
419
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00009-of-00019.bin",
420
+ "transformer.h.31.self_attention.query_key_value.SCB": "pytorch_model-00009-of-00019.bin",
421
+ "transformer.h.31.self_attention.query_key_value.bias": "pytorch_model-00009-of-00019.bin",
422
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00009-of-00019.bin",
423
+ "transformer.h.32.input_layernorm.bias": "pytorch_model-00009-of-00019.bin",
424
+ "transformer.h.32.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
425
+ "transformer.h.32.mlp.dense_4h_to_h.SCB": "pytorch_model-00009-of-00019.bin",
426
+ "transformer.h.32.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00019.bin",
427
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00019.bin",
428
+ "transformer.h.32.mlp.dense_h_to_4h.SCB": "pytorch_model-00009-of-00019.bin",
429
+ "transformer.h.32.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00019.bin",
430
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00019.bin",
431
+ "transformer.h.32.post_attention_layernorm.bias": "pytorch_model-00009-of-00019.bin",
432
+ "transformer.h.32.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
433
+ "transformer.h.32.self_attention.dense.SCB": "pytorch_model-00009-of-00019.bin",
434
+ "transformer.h.32.self_attention.dense.bias": "pytorch_model-00009-of-00019.bin",
435
+ "transformer.h.32.self_attention.dense.weight": "pytorch_model-00009-of-00019.bin",
436
+ "transformer.h.32.self_attention.query_key_value.SCB": "pytorch_model-00009-of-00019.bin",
437
+ "transformer.h.32.self_attention.query_key_value.bias": "pytorch_model-00009-of-00019.bin",
438
+ "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00009-of-00019.bin",
439
+ "transformer.h.33.input_layernorm.bias": "pytorch_model-00009-of-00019.bin",
440
+ "transformer.h.33.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
441
+ "transformer.h.33.mlp.dense_4h_to_h.SCB": "pytorch_model-00010-of-00019.bin",
442
+ "transformer.h.33.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00019.bin",
443
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00019.bin",
444
+ "transformer.h.33.mlp.dense_h_to_4h.SCB": "pytorch_model-00010-of-00019.bin",
445
+ "transformer.h.33.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00019.bin",
446
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00019.bin",
447
+ "transformer.h.33.post_attention_layernorm.bias": "pytorch_model-00010-of-00019.bin",
448
+ "transformer.h.33.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
449
+ "transformer.h.33.self_attention.dense.SCB": "pytorch_model-00010-of-00019.bin",
450
+ "transformer.h.33.self_attention.dense.bias": "pytorch_model-00010-of-00019.bin",
451
+ "transformer.h.33.self_attention.dense.weight": "pytorch_model-00010-of-00019.bin",
452
+ "transformer.h.33.self_attention.query_key_value.SCB": "pytorch_model-00010-of-00019.bin",
453
+ "transformer.h.33.self_attention.query_key_value.bias": "pytorch_model-00010-of-00019.bin",
454
+ "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00010-of-00019.bin",
455
+ "transformer.h.34.input_layernorm.bias": "pytorch_model-00010-of-00019.bin",
456
+ "transformer.h.34.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
457
+ "transformer.h.34.mlp.dense_4h_to_h.SCB": "pytorch_model-00010-of-00019.bin",
458
+ "transformer.h.34.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00019.bin",
459
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00019.bin",
460
+ "transformer.h.34.mlp.dense_h_to_4h.SCB": "pytorch_model-00010-of-00019.bin",
461
+ "transformer.h.34.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00019.bin",
462
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00019.bin",
463
+ "transformer.h.34.post_attention_layernorm.bias": "pytorch_model-00010-of-00019.bin",
464
+ "transformer.h.34.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
465
+ "transformer.h.34.self_attention.dense.SCB": "pytorch_model-00010-of-00019.bin",
466
+ "transformer.h.34.self_attention.dense.bias": "pytorch_model-00010-of-00019.bin",
467
+ "transformer.h.34.self_attention.dense.weight": "pytorch_model-00010-of-00019.bin",
468
+ "transformer.h.34.self_attention.query_key_value.SCB": "pytorch_model-00010-of-00019.bin",
469
+ "transformer.h.34.self_attention.query_key_value.bias": "pytorch_model-00010-of-00019.bin",
470
+ "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00010-of-00019.bin",
471
+ "transformer.h.35.input_layernorm.bias": "pytorch_model-00010-of-00019.bin",
472
+ "transformer.h.35.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
473
+ "transformer.h.35.mlp.dense_4h_to_h.SCB": "pytorch_model-00010-of-00019.bin",
474
+ "transformer.h.35.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00019.bin",
475
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00019.bin",
476
+ "transformer.h.35.mlp.dense_h_to_4h.SCB": "pytorch_model-00010-of-00019.bin",
477
+ "transformer.h.35.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00019.bin",
478
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00019.bin",
479
+ "transformer.h.35.post_attention_layernorm.bias": "pytorch_model-00010-of-00019.bin",
480
+ "transformer.h.35.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
481
+ "transformer.h.35.self_attention.dense.SCB": "pytorch_model-00010-of-00019.bin",
482
+ "transformer.h.35.self_attention.dense.bias": "pytorch_model-00010-of-00019.bin",
483
+ "transformer.h.35.self_attention.dense.weight": "pytorch_model-00010-of-00019.bin",
484
+ "transformer.h.35.self_attention.query_key_value.SCB": "pytorch_model-00010-of-00019.bin",
485
+ "transformer.h.35.self_attention.query_key_value.bias": "pytorch_model-00010-of-00019.bin",
486
+ "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00010-of-00019.bin",
487
+ "transformer.h.36.input_layernorm.bias": "pytorch_model-00010-of-00019.bin",
488
+ "transformer.h.36.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
489
+ "transformer.h.36.mlp.dense_4h_to_h.SCB": "pytorch_model-00010-of-00019.bin",
490
+ "transformer.h.36.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00019.bin",
491
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00019.bin",
492
+ "transformer.h.36.mlp.dense_h_to_4h.SCB": "pytorch_model-00010-of-00019.bin",
493
+ "transformer.h.36.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00019.bin",
494
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00019.bin",
495
+ "transformer.h.36.post_attention_layernorm.bias": "pytorch_model-00010-of-00019.bin",
496
+ "transformer.h.36.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
497
+ "transformer.h.36.self_attention.dense.SCB": "pytorch_model-00010-of-00019.bin",
498
+ "transformer.h.36.self_attention.dense.bias": "pytorch_model-00010-of-00019.bin",
499
+ "transformer.h.36.self_attention.dense.weight": "pytorch_model-00010-of-00019.bin",
500
+ "transformer.h.36.self_attention.query_key_value.SCB": "pytorch_model-00010-of-00019.bin",
501
+ "transformer.h.36.self_attention.query_key_value.bias": "pytorch_model-00010-of-00019.bin",
502
+ "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00010-of-00019.bin",
503
+ "transformer.h.37.input_layernorm.bias": "pytorch_model-00010-of-00019.bin",
504
+ "transformer.h.37.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
505
+ "transformer.h.37.mlp.dense_4h_to_h.SCB": "pytorch_model-00011-of-00019.bin",
506
+ "transformer.h.37.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00019.bin",
507
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00019.bin",
508
+ "transformer.h.37.mlp.dense_h_to_4h.SCB": "pytorch_model-00011-of-00019.bin",
509
+ "transformer.h.37.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00019.bin",
510
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00019.bin",
511
+ "transformer.h.37.post_attention_layernorm.bias": "pytorch_model-00011-of-00019.bin",
512
+ "transformer.h.37.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
513
+ "transformer.h.37.self_attention.dense.SCB": "pytorch_model-00011-of-00019.bin",
514
+ "transformer.h.37.self_attention.dense.bias": "pytorch_model-00011-of-00019.bin",
515
+ "transformer.h.37.self_attention.dense.weight": "pytorch_model-00011-of-00019.bin",
516
+ "transformer.h.37.self_attention.query_key_value.SCB": "pytorch_model-00011-of-00019.bin",
517
+ "transformer.h.37.self_attention.query_key_value.bias": "pytorch_model-00011-of-00019.bin",
518
+ "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00011-of-00019.bin",
519
+ "transformer.h.38.input_layernorm.bias": "pytorch_model-00011-of-00019.bin",
520
+ "transformer.h.38.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
521
+ "transformer.h.38.mlp.dense_4h_to_h.SCB": "pytorch_model-00011-of-00019.bin",
522
+ "transformer.h.38.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00019.bin",
523
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00019.bin",
524
+ "transformer.h.38.mlp.dense_h_to_4h.SCB": "pytorch_model-00011-of-00019.bin",
525
+ "transformer.h.38.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00019.bin",
526
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00019.bin",
527
+ "transformer.h.38.post_attention_layernorm.bias": "pytorch_model-00011-of-00019.bin",
528
+ "transformer.h.38.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
529
+ "transformer.h.38.self_attention.dense.SCB": "pytorch_model-00011-of-00019.bin",
530
+ "transformer.h.38.self_attention.dense.bias": "pytorch_model-00011-of-00019.bin",
531
+ "transformer.h.38.self_attention.dense.weight": "pytorch_model-00011-of-00019.bin",
532
+ "transformer.h.38.self_attention.query_key_value.SCB": "pytorch_model-00011-of-00019.bin",
533
+ "transformer.h.38.self_attention.query_key_value.bias": "pytorch_model-00011-of-00019.bin",
534
+ "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00011-of-00019.bin",
535
+ "transformer.h.39.input_layernorm.bias": "pytorch_model-00011-of-00019.bin",
536
+ "transformer.h.39.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
537
+ "transformer.h.39.mlp.dense_4h_to_h.SCB": "pytorch_model-00011-of-00019.bin",
538
+ "transformer.h.39.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00019.bin",
539
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00019.bin",
540
+ "transformer.h.39.mlp.dense_h_to_4h.SCB": "pytorch_model-00011-of-00019.bin",
541
+ "transformer.h.39.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00019.bin",
542
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00019.bin",
543
+ "transformer.h.39.post_attention_layernorm.bias": "pytorch_model-00011-of-00019.bin",
544
+ "transformer.h.39.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
545
+ "transformer.h.39.self_attention.dense.SCB": "pytorch_model-00011-of-00019.bin",
546
+ "transformer.h.39.self_attention.dense.bias": "pytorch_model-00011-of-00019.bin",
547
+ "transformer.h.39.self_attention.dense.weight": "pytorch_model-00011-of-00019.bin",
548
+ "transformer.h.39.self_attention.query_key_value.SCB": "pytorch_model-00011-of-00019.bin",
549
+ "transformer.h.39.self_attention.query_key_value.bias": "pytorch_model-00011-of-00019.bin",
550
+ "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00011-of-00019.bin",
551
+ "transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00019.bin",
552
+ "transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
553
+ "transformer.h.4.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00019.bin",
554
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00019.bin",
555
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00019.bin",
556
+ "transformer.h.4.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00019.bin",
557
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00019.bin",
558
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00019.bin",
559
+ "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00002-of-00019.bin",
560
+ "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
561
+ "transformer.h.4.self_attention.dense.SCB": "pytorch_model-00002-of-00019.bin",
562
+ "transformer.h.4.self_attention.dense.bias": "pytorch_model-00002-of-00019.bin",
563
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00019.bin",
564
+ "transformer.h.4.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00019.bin",
565
+ "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00019.bin",
566
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00019.bin",
567
+ "transformer.h.40.input_layernorm.bias": "pytorch_model-00011-of-00019.bin",
568
+ "transformer.h.40.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
569
+ "transformer.h.40.mlp.dense_4h_to_h.SCB": "pytorch_model-00011-of-00019.bin",
570
+ "transformer.h.40.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00019.bin",
571
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00019.bin",
572
+ "transformer.h.40.mlp.dense_h_to_4h.SCB": "pytorch_model-00011-of-00019.bin",
573
+ "transformer.h.40.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00019.bin",
574
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00019.bin",
575
+ "transformer.h.40.post_attention_layernorm.bias": "pytorch_model-00011-of-00019.bin",
576
+ "transformer.h.40.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
577
+ "transformer.h.40.self_attention.dense.SCB": "pytorch_model-00011-of-00019.bin",
578
+ "transformer.h.40.self_attention.dense.bias": "pytorch_model-00011-of-00019.bin",
579
+ "transformer.h.40.self_attention.dense.weight": "pytorch_model-00011-of-00019.bin",
580
+ "transformer.h.40.self_attention.query_key_value.SCB": "pytorch_model-00011-of-00019.bin",
581
+ "transformer.h.40.self_attention.query_key_value.bias": "pytorch_model-00011-of-00019.bin",
582
+ "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00011-of-00019.bin",
583
+ "transformer.h.41.input_layernorm.bias": "pytorch_model-00011-of-00019.bin",
584
+ "transformer.h.41.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
585
+ "transformer.h.41.mlp.dense_4h_to_h.SCB": "pytorch_model-00012-of-00019.bin",
586
+ "transformer.h.41.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00019.bin",
587
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00019.bin",
588
+ "transformer.h.41.mlp.dense_h_to_4h.SCB": "pytorch_model-00012-of-00019.bin",
589
+ "transformer.h.41.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00019.bin",
590
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00019.bin",
591
+ "transformer.h.41.post_attention_layernorm.bias": "pytorch_model-00012-of-00019.bin",
592
+ "transformer.h.41.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
593
+ "transformer.h.41.self_attention.dense.SCB": "pytorch_model-00012-of-00019.bin",
594
+ "transformer.h.41.self_attention.dense.bias": "pytorch_model-00012-of-00019.bin",
595
+ "transformer.h.41.self_attention.dense.weight": "pytorch_model-00012-of-00019.bin",
596
+ "transformer.h.41.self_attention.query_key_value.SCB": "pytorch_model-00012-of-00019.bin",
597
+ "transformer.h.41.self_attention.query_key_value.bias": "pytorch_model-00012-of-00019.bin",
598
+ "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00012-of-00019.bin",
599
+ "transformer.h.42.input_layernorm.bias": "pytorch_model-00012-of-00019.bin",
600
+ "transformer.h.42.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
601
+ "transformer.h.42.mlp.dense_4h_to_h.SCB": "pytorch_model-00012-of-00019.bin",
602
+ "transformer.h.42.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00019.bin",
603
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00019.bin",
604
+ "transformer.h.42.mlp.dense_h_to_4h.SCB": "pytorch_model-00012-of-00019.bin",
605
+ "transformer.h.42.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00019.bin",
606
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00019.bin",
607
+ "transformer.h.42.post_attention_layernorm.bias": "pytorch_model-00012-of-00019.bin",
608
+ "transformer.h.42.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
609
+ "transformer.h.42.self_attention.dense.SCB": "pytorch_model-00012-of-00019.bin",
610
+ "transformer.h.42.self_attention.dense.bias": "pytorch_model-00012-of-00019.bin",
611
+ "transformer.h.42.self_attention.dense.weight": "pytorch_model-00012-of-00019.bin",
612
+ "transformer.h.42.self_attention.query_key_value.SCB": "pytorch_model-00012-of-00019.bin",
613
+ "transformer.h.42.self_attention.query_key_value.bias": "pytorch_model-00012-of-00019.bin",
614
+ "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00012-of-00019.bin",
615
+ "transformer.h.43.input_layernorm.bias": "pytorch_model-00012-of-00019.bin",
616
+ "transformer.h.43.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
617
+ "transformer.h.43.mlp.dense_4h_to_h.SCB": "pytorch_model-00012-of-00019.bin",
618
+ "transformer.h.43.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00019.bin",
619
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00019.bin",
620
+ "transformer.h.43.mlp.dense_h_to_4h.SCB": "pytorch_model-00012-of-00019.bin",
621
+ "transformer.h.43.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00019.bin",
622
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00019.bin",
623
+ "transformer.h.43.post_attention_layernorm.bias": "pytorch_model-00012-of-00019.bin",
624
+ "transformer.h.43.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
625
+ "transformer.h.43.self_attention.dense.SCB": "pytorch_model-00012-of-00019.bin",
626
+ "transformer.h.43.self_attention.dense.bias": "pytorch_model-00012-of-00019.bin",
627
+ "transformer.h.43.self_attention.dense.weight": "pytorch_model-00012-of-00019.bin",
628
+ "transformer.h.43.self_attention.query_key_value.SCB": "pytorch_model-00012-of-00019.bin",
629
+ "transformer.h.43.self_attention.query_key_value.bias": "pytorch_model-00012-of-00019.bin",
630
+ "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00012-of-00019.bin",
631
+ "transformer.h.44.input_layernorm.bias": "pytorch_model-00012-of-00019.bin",
632
+ "transformer.h.44.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
633
+ "transformer.h.44.mlp.dense_4h_to_h.SCB": "pytorch_model-00012-of-00019.bin",
634
+ "transformer.h.44.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00019.bin",
635
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00019.bin",
636
+ "transformer.h.44.mlp.dense_h_to_4h.SCB": "pytorch_model-00012-of-00019.bin",
637
+ "transformer.h.44.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00019.bin",
638
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00019.bin",
639
+ "transformer.h.44.post_attention_layernorm.bias": "pytorch_model-00012-of-00019.bin",
640
+ "transformer.h.44.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
641
+ "transformer.h.44.self_attention.dense.SCB": "pytorch_model-00012-of-00019.bin",
642
+ "transformer.h.44.self_attention.dense.bias": "pytorch_model-00012-of-00019.bin",
643
+ "transformer.h.44.self_attention.dense.weight": "pytorch_model-00012-of-00019.bin",
644
+ "transformer.h.44.self_attention.query_key_value.SCB": "pytorch_model-00012-of-00019.bin",
645
+ "transformer.h.44.self_attention.query_key_value.bias": "pytorch_model-00012-of-00019.bin",
646
+ "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00012-of-00019.bin",
647
+ "transformer.h.45.input_layernorm.bias": "pytorch_model-00012-of-00019.bin",
648
+ "transformer.h.45.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
649
+ "transformer.h.45.mlp.dense_4h_to_h.SCB": "pytorch_model-00013-of-00019.bin",
650
+ "transformer.h.45.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00019.bin",
651
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00019.bin",
652
+ "transformer.h.45.mlp.dense_h_to_4h.SCB": "pytorch_model-00013-of-00019.bin",
653
+ "transformer.h.45.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00019.bin",
654
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00019.bin",
655
+ "transformer.h.45.post_attention_layernorm.bias": "pytorch_model-00013-of-00019.bin",
656
+ "transformer.h.45.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
657
+ "transformer.h.45.self_attention.dense.SCB": "pytorch_model-00013-of-00019.bin",
658
+ "transformer.h.45.self_attention.dense.bias": "pytorch_model-00013-of-00019.bin",
659
+ "transformer.h.45.self_attention.dense.weight": "pytorch_model-00013-of-00019.bin",
660
+ "transformer.h.45.self_attention.query_key_value.SCB": "pytorch_model-00013-of-00019.bin",
661
+ "transformer.h.45.self_attention.query_key_value.bias": "pytorch_model-00013-of-00019.bin",
662
+ "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00013-of-00019.bin",
663
+ "transformer.h.46.input_layernorm.bias": "pytorch_model-00013-of-00019.bin",
664
+ "transformer.h.46.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
665
+ "transformer.h.46.mlp.dense_4h_to_h.SCB": "pytorch_model-00013-of-00019.bin",
666
+ "transformer.h.46.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00019.bin",
667
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00019.bin",
668
+ "transformer.h.46.mlp.dense_h_to_4h.SCB": "pytorch_model-00013-of-00019.bin",
669
+ "transformer.h.46.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00019.bin",
670
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00019.bin",
671
+ "transformer.h.46.post_attention_layernorm.bias": "pytorch_model-00013-of-00019.bin",
672
+ "transformer.h.46.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
673
+ "transformer.h.46.self_attention.dense.SCB": "pytorch_model-00013-of-00019.bin",
674
+ "transformer.h.46.self_attention.dense.bias": "pytorch_model-00013-of-00019.bin",
675
+ "transformer.h.46.self_attention.dense.weight": "pytorch_model-00013-of-00019.bin",
676
+ "transformer.h.46.self_attention.query_key_value.SCB": "pytorch_model-00013-of-00019.bin",
677
+ "transformer.h.46.self_attention.query_key_value.bias": "pytorch_model-00013-of-00019.bin",
678
+ "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00013-of-00019.bin",
679
+ "transformer.h.47.input_layernorm.bias": "pytorch_model-00013-of-00019.bin",
680
+ "transformer.h.47.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
681
+ "transformer.h.47.mlp.dense_4h_to_h.SCB": "pytorch_model-00013-of-00019.bin",
682
+ "transformer.h.47.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00019.bin",
683
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00019.bin",
684
+ "transformer.h.47.mlp.dense_h_to_4h.SCB": "pytorch_model-00013-of-00019.bin",
685
+ "transformer.h.47.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00019.bin",
686
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00019.bin",
687
+ "transformer.h.47.post_attention_layernorm.bias": "pytorch_model-00013-of-00019.bin",
688
+ "transformer.h.47.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
689
+ "transformer.h.47.self_attention.dense.SCB": "pytorch_model-00013-of-00019.bin",
690
+ "transformer.h.47.self_attention.dense.bias": "pytorch_model-00013-of-00019.bin",
691
+ "transformer.h.47.self_attention.dense.weight": "pytorch_model-00013-of-00019.bin",
692
+ "transformer.h.47.self_attention.query_key_value.SCB": "pytorch_model-00013-of-00019.bin",
693
+ "transformer.h.47.self_attention.query_key_value.bias": "pytorch_model-00013-of-00019.bin",
694
+ "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00013-of-00019.bin",
695
+ "transformer.h.48.input_layernorm.bias": "pytorch_model-00013-of-00019.bin",
696
+ "transformer.h.48.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
697
+ "transformer.h.48.mlp.dense_4h_to_h.SCB": "pytorch_model-00013-of-00019.bin",
698
+ "transformer.h.48.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00019.bin",
699
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00019.bin",
700
+ "transformer.h.48.mlp.dense_h_to_4h.SCB": "pytorch_model-00013-of-00019.bin",
701
+ "transformer.h.48.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00019.bin",
702
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00019.bin",
703
+ "transformer.h.48.post_attention_layernorm.bias": "pytorch_model-00013-of-00019.bin",
704
+ "transformer.h.48.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
705
+ "transformer.h.48.self_attention.dense.SCB": "pytorch_model-00013-of-00019.bin",
706
+ "transformer.h.48.self_attention.dense.bias": "pytorch_model-00013-of-00019.bin",
707
+ "transformer.h.48.self_attention.dense.weight": "pytorch_model-00013-of-00019.bin",
708
+ "transformer.h.48.self_attention.query_key_value.SCB": "pytorch_model-00013-of-00019.bin",
709
+ "transformer.h.48.self_attention.query_key_value.bias": "pytorch_model-00013-of-00019.bin",
710
+ "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00013-of-00019.bin",
711
+ "transformer.h.49.input_layernorm.bias": "pytorch_model-00013-of-00019.bin",
712
+ "transformer.h.49.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
713
+ "transformer.h.49.mlp.dense_4h_to_h.SCB": "pytorch_model-00014-of-00019.bin",
714
+ "transformer.h.49.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00019.bin",
715
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00019.bin",
716
+ "transformer.h.49.mlp.dense_h_to_4h.SCB": "pytorch_model-00014-of-00019.bin",
717
+ "transformer.h.49.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00019.bin",
718
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00019.bin",
719
+ "transformer.h.49.post_attention_layernorm.bias": "pytorch_model-00014-of-00019.bin",
720
+ "transformer.h.49.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
721
+ "transformer.h.49.self_attention.dense.SCB": "pytorch_model-00014-of-00019.bin",
722
+ "transformer.h.49.self_attention.dense.bias": "pytorch_model-00014-of-00019.bin",
723
+ "transformer.h.49.self_attention.dense.weight": "pytorch_model-00014-of-00019.bin",
724
+ "transformer.h.49.self_attention.query_key_value.SCB": "pytorch_model-00014-of-00019.bin",
725
+ "transformer.h.49.self_attention.query_key_value.bias": "pytorch_model-00014-of-00019.bin",
726
+ "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00014-of-00019.bin",
727
+ "transformer.h.5.input_layernorm.bias": "pytorch_model-00002-of-00019.bin",
728
+ "transformer.h.5.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
729
+ "transformer.h.5.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00019.bin",
730
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00019.bin",
731
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00019.bin",
732
+ "transformer.h.5.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00019.bin",
733
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00019.bin",
734
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00019.bin",
735
+ "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00019.bin",
736
+ "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
737
+ "transformer.h.5.self_attention.dense.SCB": "pytorch_model-00003-of-00019.bin",
738
+ "transformer.h.5.self_attention.dense.bias": "pytorch_model-00003-of-00019.bin",
739
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00019.bin",
740
+ "transformer.h.5.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00019.bin",
741
+ "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00003-of-00019.bin",
742
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00019.bin",
743
+ "transformer.h.50.input_layernorm.bias": "pytorch_model-00014-of-00019.bin",
744
+ "transformer.h.50.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
745
+ "transformer.h.50.mlp.dense_4h_to_h.SCB": "pytorch_model-00014-of-00019.bin",
746
+ "transformer.h.50.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00019.bin",
747
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00019.bin",
748
+ "transformer.h.50.mlp.dense_h_to_4h.SCB": "pytorch_model-00014-of-00019.bin",
749
+ "transformer.h.50.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00019.bin",
750
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00019.bin",
751
+ "transformer.h.50.post_attention_layernorm.bias": "pytorch_model-00014-of-00019.bin",
752
+ "transformer.h.50.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
753
+ "transformer.h.50.self_attention.dense.SCB": "pytorch_model-00014-of-00019.bin",
754
+ "transformer.h.50.self_attention.dense.bias": "pytorch_model-00014-of-00019.bin",
755
+ "transformer.h.50.self_attention.dense.weight": "pytorch_model-00014-of-00019.bin",
756
+ "transformer.h.50.self_attention.query_key_value.SCB": "pytorch_model-00014-of-00019.bin",
757
+ "transformer.h.50.self_attention.query_key_value.bias": "pytorch_model-00014-of-00019.bin",
758
+ "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00014-of-00019.bin",
759
+ "transformer.h.51.input_layernorm.bias": "pytorch_model-00014-of-00019.bin",
760
+ "transformer.h.51.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
761
+ "transformer.h.51.mlp.dense_4h_to_h.SCB": "pytorch_model-00014-of-00019.bin",
762
+ "transformer.h.51.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00019.bin",
763
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00019.bin",
764
+ "transformer.h.51.mlp.dense_h_to_4h.SCB": "pytorch_model-00014-of-00019.bin",
765
+ "transformer.h.51.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00019.bin",
766
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00019.bin",
767
+ "transformer.h.51.post_attention_layernorm.bias": "pytorch_model-00014-of-00019.bin",
768
+ "transformer.h.51.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
769
+ "transformer.h.51.self_attention.dense.SCB": "pytorch_model-00014-of-00019.bin",
770
+ "transformer.h.51.self_attention.dense.bias": "pytorch_model-00014-of-00019.bin",
771
+ "transformer.h.51.self_attention.dense.weight": "pytorch_model-00014-of-00019.bin",
772
+ "transformer.h.51.self_attention.query_key_value.SCB": "pytorch_model-00014-of-00019.bin",
773
+ "transformer.h.51.self_attention.query_key_value.bias": "pytorch_model-00014-of-00019.bin",
774
+ "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00014-of-00019.bin",
775
+ "transformer.h.52.input_layernorm.bias": "pytorch_model-00014-of-00019.bin",
776
+ "transformer.h.52.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
777
+ "transformer.h.52.mlp.dense_4h_to_h.SCB": "pytorch_model-00014-of-00019.bin",
778
+ "transformer.h.52.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00019.bin",
779
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00019.bin",
780
+ "transformer.h.52.mlp.dense_h_to_4h.SCB": "pytorch_model-00014-of-00019.bin",
781
+ "transformer.h.52.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00019.bin",
782
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00019.bin",
783
+ "transformer.h.52.post_attention_layernorm.bias": "pytorch_model-00014-of-00019.bin",
784
+ "transformer.h.52.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
785
+ "transformer.h.52.self_attention.dense.SCB": "pytorch_model-00014-of-00019.bin",
786
+ "transformer.h.52.self_attention.dense.bias": "pytorch_model-00014-of-00019.bin",
787
+ "transformer.h.52.self_attention.dense.weight": "pytorch_model-00014-of-00019.bin",
788
+ "transformer.h.52.self_attention.query_key_value.SCB": "pytorch_model-00014-of-00019.bin",
789
+ "transformer.h.52.self_attention.query_key_value.bias": "pytorch_model-00014-of-00019.bin",
790
+ "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00014-of-00019.bin",
791
+ "transformer.h.53.input_layernorm.bias": "pytorch_model-00014-of-00019.bin",
792
+ "transformer.h.53.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
793
+ "transformer.h.53.mlp.dense_4h_to_h.SCB": "pytorch_model-00015-of-00019.bin",
794
+ "transformer.h.53.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00019.bin",
795
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00019.bin",
796
+ "transformer.h.53.mlp.dense_h_to_4h.SCB": "pytorch_model-00015-of-00019.bin",
797
+ "transformer.h.53.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00019.bin",
798
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00019.bin",
799
+ "transformer.h.53.post_attention_layernorm.bias": "pytorch_model-00015-of-00019.bin",
800
+ "transformer.h.53.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
801
+ "transformer.h.53.self_attention.dense.SCB": "pytorch_model-00015-of-00019.bin",
802
+ "transformer.h.53.self_attention.dense.bias": "pytorch_model-00015-of-00019.bin",
803
+ "transformer.h.53.self_attention.dense.weight": "pytorch_model-00015-of-00019.bin",
804
+ "transformer.h.53.self_attention.query_key_value.SCB": "pytorch_model-00015-of-00019.bin",
805
+ "transformer.h.53.self_attention.query_key_value.bias": "pytorch_model-00015-of-00019.bin",
806
+ "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00015-of-00019.bin",
807
+ "transformer.h.54.input_layernorm.bias": "pytorch_model-00015-of-00019.bin",
808
+ "transformer.h.54.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
809
+ "transformer.h.54.mlp.dense_4h_to_h.SCB": "pytorch_model-00015-of-00019.bin",
810
+ "transformer.h.54.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00019.bin",
811
+ "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00019.bin",
812
+ "transformer.h.54.mlp.dense_h_to_4h.SCB": "pytorch_model-00015-of-00019.bin",
813
+ "transformer.h.54.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00019.bin",
814
+ "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00019.bin",
815
+ "transformer.h.54.post_attention_layernorm.bias": "pytorch_model-00015-of-00019.bin",
816
+ "transformer.h.54.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
817
+ "transformer.h.54.self_attention.dense.SCB": "pytorch_model-00015-of-00019.bin",
818
+ "transformer.h.54.self_attention.dense.bias": "pytorch_model-00015-of-00019.bin",
819
+ "transformer.h.54.self_attention.dense.weight": "pytorch_model-00015-of-00019.bin",
820
+ "transformer.h.54.self_attention.query_key_value.SCB": "pytorch_model-00015-of-00019.bin",
821
+ "transformer.h.54.self_attention.query_key_value.bias": "pytorch_model-00015-of-00019.bin",
822
+ "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00015-of-00019.bin",
823
+ "transformer.h.55.input_layernorm.bias": "pytorch_model-00015-of-00019.bin",
824
+ "transformer.h.55.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
825
+ "transformer.h.55.mlp.dense_4h_to_h.SCB": "pytorch_model-00015-of-00019.bin",
826
+ "transformer.h.55.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00019.bin",
827
+ "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00019.bin",
828
+ "transformer.h.55.mlp.dense_h_to_4h.SCB": "pytorch_model-00015-of-00019.bin",
829
+ "transformer.h.55.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00019.bin",
830
+ "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00019.bin",
831
+ "transformer.h.55.post_attention_layernorm.bias": "pytorch_model-00015-of-00019.bin",
832
+ "transformer.h.55.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
833
+ "transformer.h.55.self_attention.dense.SCB": "pytorch_model-00015-of-00019.bin",
834
+ "transformer.h.55.self_attention.dense.bias": "pytorch_model-00015-of-00019.bin",
835
+ "transformer.h.55.self_attention.dense.weight": "pytorch_model-00015-of-00019.bin",
836
+ "transformer.h.55.self_attention.query_key_value.SCB": "pytorch_model-00015-of-00019.bin",
837
+ "transformer.h.55.self_attention.query_key_value.bias": "pytorch_model-00015-of-00019.bin",
838
+ "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00015-of-00019.bin",
839
+ "transformer.h.56.input_layernorm.bias": "pytorch_model-00015-of-00019.bin",
840
+ "transformer.h.56.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
841
+ "transformer.h.56.mlp.dense_4h_to_h.SCB": "pytorch_model-00015-of-00019.bin",
842
+ "transformer.h.56.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00019.bin",
843
+ "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00019.bin",
844
+ "transformer.h.56.mlp.dense_h_to_4h.SCB": "pytorch_model-00015-of-00019.bin",
845
+ "transformer.h.56.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00019.bin",
846
+ "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00019.bin",
847
+ "transformer.h.56.post_attention_layernorm.bias": "pytorch_model-00015-of-00019.bin",
848
+ "transformer.h.56.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
849
+ "transformer.h.56.self_attention.dense.SCB": "pytorch_model-00015-of-00019.bin",
850
+ "transformer.h.56.self_attention.dense.bias": "pytorch_model-00015-of-00019.bin",
851
+ "transformer.h.56.self_attention.dense.weight": "pytorch_model-00015-of-00019.bin",
852
+ "transformer.h.56.self_attention.query_key_value.SCB": "pytorch_model-00015-of-00019.bin",
853
+ "transformer.h.56.self_attention.query_key_value.bias": "pytorch_model-00015-of-00019.bin",
854
+ "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00015-of-00019.bin",
855
+ "transformer.h.57.input_layernorm.bias": "pytorch_model-00015-of-00019.bin",
856
+ "transformer.h.57.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
857
+ "transformer.h.57.mlp.dense_4h_to_h.SCB": "pytorch_model-00016-of-00019.bin",
858
+ "transformer.h.57.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00019.bin",
859
+ "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00019.bin",
860
+ "transformer.h.57.mlp.dense_h_to_4h.SCB": "pytorch_model-00016-of-00019.bin",
861
+ "transformer.h.57.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00019.bin",
862
+ "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00019.bin",
863
+ "transformer.h.57.post_attention_layernorm.bias": "pytorch_model-00016-of-00019.bin",
864
+ "transformer.h.57.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
865
+ "transformer.h.57.self_attention.dense.SCB": "pytorch_model-00016-of-00019.bin",
866
+ "transformer.h.57.self_attention.dense.bias": "pytorch_model-00016-of-00019.bin",
867
+ "transformer.h.57.self_attention.dense.weight": "pytorch_model-00016-of-00019.bin",
868
+ "transformer.h.57.self_attention.query_key_value.SCB": "pytorch_model-00016-of-00019.bin",
869
+ "transformer.h.57.self_attention.query_key_value.bias": "pytorch_model-00016-of-00019.bin",
870
+ "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00016-of-00019.bin",
871
+ "transformer.h.58.input_layernorm.bias": "pytorch_model-00016-of-00019.bin",
872
+ "transformer.h.58.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
873
+ "transformer.h.58.mlp.dense_4h_to_h.SCB": "pytorch_model-00016-of-00019.bin",
874
+ "transformer.h.58.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00019.bin",
875
+ "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00019.bin",
876
+ "transformer.h.58.mlp.dense_h_to_4h.SCB": "pytorch_model-00016-of-00019.bin",
877
+ "transformer.h.58.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00019.bin",
878
+ "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00019.bin",
879
+ "transformer.h.58.post_attention_layernorm.bias": "pytorch_model-00016-of-00019.bin",
880
+ "transformer.h.58.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
881
+ "transformer.h.58.self_attention.dense.SCB": "pytorch_model-00016-of-00019.bin",
882
+ "transformer.h.58.self_attention.dense.bias": "pytorch_model-00016-of-00019.bin",
883
+ "transformer.h.58.self_attention.dense.weight": "pytorch_model-00016-of-00019.bin",
884
+ "transformer.h.58.self_attention.query_key_value.SCB": "pytorch_model-00016-of-00019.bin",
885
+ "transformer.h.58.self_attention.query_key_value.bias": "pytorch_model-00016-of-00019.bin",
886
+ "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00016-of-00019.bin",
887
+ "transformer.h.59.input_layernorm.bias": "pytorch_model-00016-of-00019.bin",
888
+ "transformer.h.59.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
889
+ "transformer.h.59.mlp.dense_4h_to_h.SCB": "pytorch_model-00016-of-00019.bin",
890
+ "transformer.h.59.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00019.bin",
891
+ "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00019.bin",
892
+ "transformer.h.59.mlp.dense_h_to_4h.SCB": "pytorch_model-00016-of-00019.bin",
893
+ "transformer.h.59.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00019.bin",
894
+ "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00019.bin",
895
+ "transformer.h.59.post_attention_layernorm.bias": "pytorch_model-00016-of-00019.bin",
896
+ "transformer.h.59.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
897
+ "transformer.h.59.self_attention.dense.SCB": "pytorch_model-00016-of-00019.bin",
898
+ "transformer.h.59.self_attention.dense.bias": "pytorch_model-00016-of-00019.bin",
899
+ "transformer.h.59.self_attention.dense.weight": "pytorch_model-00016-of-00019.bin",
900
+ "transformer.h.59.self_attention.query_key_value.SCB": "pytorch_model-00016-of-00019.bin",
901
+ "transformer.h.59.self_attention.query_key_value.bias": "pytorch_model-00016-of-00019.bin",
902
+ "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00016-of-00019.bin",
903
+ "transformer.h.6.input_layernorm.bias": "pytorch_model-00003-of-00019.bin",
904
+ "transformer.h.6.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
905
+ "transformer.h.6.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00019.bin",
906
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00019.bin",
907
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00019.bin",
908
+ "transformer.h.6.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00019.bin",
909
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00019.bin",
910
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00019.bin",
911
+ "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00003-of-00019.bin",
912
+ "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
913
+ "transformer.h.6.self_attention.dense.SCB": "pytorch_model-00003-of-00019.bin",
914
+ "transformer.h.6.self_attention.dense.bias": "pytorch_model-00003-of-00019.bin",
915
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00003-of-00019.bin",
916
+ "transformer.h.6.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00019.bin",
917
+ "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00003-of-00019.bin",
918
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00003-of-00019.bin",
919
+ "transformer.h.60.input_layernorm.bias": "pytorch_model-00016-of-00019.bin",
920
+ "transformer.h.60.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
921
+ "transformer.h.60.mlp.dense_4h_to_h.SCB": "pytorch_model-00016-of-00019.bin",
922
+ "transformer.h.60.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00019.bin",
923
+ "transformer.h.60.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00019.bin",
924
+ "transformer.h.60.mlp.dense_h_to_4h.SCB": "pytorch_model-00016-of-00019.bin",
925
+ "transformer.h.60.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00019.bin",
926
+ "transformer.h.60.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00019.bin",
927
+ "transformer.h.60.post_attention_layernorm.bias": "pytorch_model-00016-of-00019.bin",
928
+ "transformer.h.60.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
929
+ "transformer.h.60.self_attention.dense.SCB": "pytorch_model-00016-of-00019.bin",
930
+ "transformer.h.60.self_attention.dense.bias": "pytorch_model-00016-of-00019.bin",
931
+ "transformer.h.60.self_attention.dense.weight": "pytorch_model-00016-of-00019.bin",
932
+ "transformer.h.60.self_attention.query_key_value.SCB": "pytorch_model-00016-of-00019.bin",
933
+ "transformer.h.60.self_attention.query_key_value.bias": "pytorch_model-00016-of-00019.bin",
934
+ "transformer.h.60.self_attention.query_key_value.weight": "pytorch_model-00016-of-00019.bin",
935
+ "transformer.h.61.input_layernorm.bias": "pytorch_model-00016-of-00019.bin",
936
+ "transformer.h.61.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
937
+ "transformer.h.61.mlp.dense_4h_to_h.SCB": "pytorch_model-00017-of-00019.bin",
938
+ "transformer.h.61.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00019.bin",
939
+ "transformer.h.61.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00019.bin",
940
+ "transformer.h.61.mlp.dense_h_to_4h.SCB": "pytorch_model-00017-of-00019.bin",
941
+ "transformer.h.61.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00019.bin",
942
+ "transformer.h.61.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00019.bin",
943
+ "transformer.h.61.post_attention_layernorm.bias": "pytorch_model-00017-of-00019.bin",
944
+ "transformer.h.61.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
945
+ "transformer.h.61.self_attention.dense.SCB": "pytorch_model-00017-of-00019.bin",
946
+ "transformer.h.61.self_attention.dense.bias": "pytorch_model-00017-of-00019.bin",
947
+ "transformer.h.61.self_attention.dense.weight": "pytorch_model-00017-of-00019.bin",
948
+ "transformer.h.61.self_attention.query_key_value.SCB": "pytorch_model-00017-of-00019.bin",
949
+ "transformer.h.61.self_attention.query_key_value.bias": "pytorch_model-00017-of-00019.bin",
950
+ "transformer.h.61.self_attention.query_key_value.weight": "pytorch_model-00017-of-00019.bin",
951
+ "transformer.h.62.input_layernorm.bias": "pytorch_model-00017-of-00019.bin",
952
+ "transformer.h.62.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
953
+ "transformer.h.62.mlp.dense_4h_to_h.SCB": "pytorch_model-00017-of-00019.bin",
954
+ "transformer.h.62.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00019.bin",
955
+ "transformer.h.62.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00019.bin",
956
+ "transformer.h.62.mlp.dense_h_to_4h.SCB": "pytorch_model-00017-of-00019.bin",
957
+ "transformer.h.62.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00019.bin",
958
+ "transformer.h.62.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00019.bin",
959
+ "transformer.h.62.post_attention_layernorm.bias": "pytorch_model-00017-of-00019.bin",
960
+ "transformer.h.62.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
961
+ "transformer.h.62.self_attention.dense.SCB": "pytorch_model-00017-of-00019.bin",
962
+ "transformer.h.62.self_attention.dense.bias": "pytorch_model-00017-of-00019.bin",
963
+ "transformer.h.62.self_attention.dense.weight": "pytorch_model-00017-of-00019.bin",
964
+ "transformer.h.62.self_attention.query_key_value.SCB": "pytorch_model-00017-of-00019.bin",
965
+ "transformer.h.62.self_attention.query_key_value.bias": "pytorch_model-00017-of-00019.bin",
966
+ "transformer.h.62.self_attention.query_key_value.weight": "pytorch_model-00017-of-00019.bin",
967
+ "transformer.h.63.input_layernorm.bias": "pytorch_model-00017-of-00019.bin",
968
+ "transformer.h.63.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
969
+ "transformer.h.63.mlp.dense_4h_to_h.SCB": "pytorch_model-00017-of-00019.bin",
970
+ "transformer.h.63.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00019.bin",
971
+ "transformer.h.63.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00019.bin",
972
+ "transformer.h.63.mlp.dense_h_to_4h.SCB": "pytorch_model-00017-of-00019.bin",
973
+ "transformer.h.63.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00019.bin",
974
+ "transformer.h.63.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00019.bin",
975
+ "transformer.h.63.post_attention_layernorm.bias": "pytorch_model-00017-of-00019.bin",
976
+ "transformer.h.63.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
977
+ "transformer.h.63.self_attention.dense.SCB": "pytorch_model-00017-of-00019.bin",
978
+ "transformer.h.63.self_attention.dense.bias": "pytorch_model-00017-of-00019.bin",
979
+ "transformer.h.63.self_attention.dense.weight": "pytorch_model-00017-of-00019.bin",
980
+ "transformer.h.63.self_attention.query_key_value.SCB": "pytorch_model-00017-of-00019.bin",
981
+ "transformer.h.63.self_attention.query_key_value.bias": "pytorch_model-00017-of-00019.bin",
982
+ "transformer.h.63.self_attention.query_key_value.weight": "pytorch_model-00017-of-00019.bin",
983
+ "transformer.h.64.input_layernorm.bias": "pytorch_model-00017-of-00019.bin",
984
+ "transformer.h.64.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
985
+ "transformer.h.64.mlp.dense_4h_to_h.SCB": "pytorch_model-00017-of-00019.bin",
986
+ "transformer.h.64.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00019.bin",
987
+ "transformer.h.64.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00019.bin",
988
+ "transformer.h.64.mlp.dense_h_to_4h.SCB": "pytorch_model-00017-of-00019.bin",
989
+ "transformer.h.64.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00019.bin",
990
+ "transformer.h.64.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00019.bin",
991
+ "transformer.h.64.post_attention_layernorm.bias": "pytorch_model-00017-of-00019.bin",
992
+ "transformer.h.64.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
993
+ "transformer.h.64.self_attention.dense.SCB": "pytorch_model-00017-of-00019.bin",
994
+ "transformer.h.64.self_attention.dense.bias": "pytorch_model-00017-of-00019.bin",
995
+ "transformer.h.64.self_attention.dense.weight": "pytorch_model-00017-of-00019.bin",
996
+ "transformer.h.64.self_attention.query_key_value.SCB": "pytorch_model-00017-of-00019.bin",
997
+ "transformer.h.64.self_attention.query_key_value.bias": "pytorch_model-00017-of-00019.bin",
998
+ "transformer.h.64.self_attention.query_key_value.weight": "pytorch_model-00017-of-00019.bin",
999
+ "transformer.h.65.input_layernorm.bias": "pytorch_model-00017-of-00019.bin",
1000
+ "transformer.h.65.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
1001
+ "transformer.h.65.mlp.dense_4h_to_h.SCB": "pytorch_model-00018-of-00019.bin",
1002
+ "transformer.h.65.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00019.bin",
1003
+ "transformer.h.65.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00019.bin",
1004
+ "transformer.h.65.mlp.dense_h_to_4h.SCB": "pytorch_model-00018-of-00019.bin",
1005
+ "transformer.h.65.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00019.bin",
1006
+ "transformer.h.65.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00019.bin",
1007
+ "transformer.h.65.post_attention_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1008
+ "transformer.h.65.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1009
+ "transformer.h.65.self_attention.dense.SCB": "pytorch_model-00018-of-00019.bin",
1010
+ "transformer.h.65.self_attention.dense.bias": "pytorch_model-00018-of-00019.bin",
1011
+ "transformer.h.65.self_attention.dense.weight": "pytorch_model-00018-of-00019.bin",
1012
+ "transformer.h.65.self_attention.query_key_value.SCB": "pytorch_model-00018-of-00019.bin",
1013
+ "transformer.h.65.self_attention.query_key_value.bias": "pytorch_model-00018-of-00019.bin",
1014
+ "transformer.h.65.self_attention.query_key_value.weight": "pytorch_model-00018-of-00019.bin",
1015
+ "transformer.h.66.input_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1016
+ "transformer.h.66.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1017
+ "transformer.h.66.mlp.dense_4h_to_h.SCB": "pytorch_model-00018-of-00019.bin",
1018
+ "transformer.h.66.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00019.bin",
1019
+ "transformer.h.66.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00019.bin",
1020
+ "transformer.h.66.mlp.dense_h_to_4h.SCB": "pytorch_model-00018-of-00019.bin",
1021
+ "transformer.h.66.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00019.bin",
1022
+ "transformer.h.66.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00019.bin",
1023
+ "transformer.h.66.post_attention_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1024
+ "transformer.h.66.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1025
+ "transformer.h.66.self_attention.dense.SCB": "pytorch_model-00018-of-00019.bin",
1026
+ "transformer.h.66.self_attention.dense.bias": "pytorch_model-00018-of-00019.bin",
1027
+ "transformer.h.66.self_attention.dense.weight": "pytorch_model-00018-of-00019.bin",
1028
+ "transformer.h.66.self_attention.query_key_value.SCB": "pytorch_model-00018-of-00019.bin",
1029
+ "transformer.h.66.self_attention.query_key_value.bias": "pytorch_model-00018-of-00019.bin",
1030
+ "transformer.h.66.self_attention.query_key_value.weight": "pytorch_model-00018-of-00019.bin",
1031
+ "transformer.h.67.input_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1032
+ "transformer.h.67.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1033
+ "transformer.h.67.mlp.dense_4h_to_h.SCB": "pytorch_model-00018-of-00019.bin",
1034
+ "transformer.h.67.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00019.bin",
1035
+ "transformer.h.67.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00019.bin",
1036
+ "transformer.h.67.mlp.dense_h_to_4h.SCB": "pytorch_model-00018-of-00019.bin",
1037
+ "transformer.h.67.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00019.bin",
1038
+ "transformer.h.67.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00019.bin",
1039
+ "transformer.h.67.post_attention_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1040
+ "transformer.h.67.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1041
+ "transformer.h.67.self_attention.dense.SCB": "pytorch_model-00018-of-00019.bin",
1042
+ "transformer.h.67.self_attention.dense.bias": "pytorch_model-00018-of-00019.bin",
1043
+ "transformer.h.67.self_attention.dense.weight": "pytorch_model-00018-of-00019.bin",
1044
+ "transformer.h.67.self_attention.query_key_value.SCB": "pytorch_model-00018-of-00019.bin",
1045
+ "transformer.h.67.self_attention.query_key_value.bias": "pytorch_model-00018-of-00019.bin",
1046
+ "transformer.h.67.self_attention.query_key_value.weight": "pytorch_model-00018-of-00019.bin",
1047
+ "transformer.h.68.input_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1048
+ "transformer.h.68.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1049
+ "transformer.h.68.mlp.dense_4h_to_h.SCB": "pytorch_model-00018-of-00019.bin",
1050
+ "transformer.h.68.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00019.bin",
1051
+ "transformer.h.68.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00019.bin",
1052
+ "transformer.h.68.mlp.dense_h_to_4h.SCB": "pytorch_model-00018-of-00019.bin",
1053
+ "transformer.h.68.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00019.bin",
1054
+ "transformer.h.68.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00019.bin",
1055
+ "transformer.h.68.post_attention_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1056
+ "transformer.h.68.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1057
+ "transformer.h.68.self_attention.dense.SCB": "pytorch_model-00018-of-00019.bin",
1058
+ "transformer.h.68.self_attention.dense.bias": "pytorch_model-00018-of-00019.bin",
1059
+ "transformer.h.68.self_attention.dense.weight": "pytorch_model-00018-of-00019.bin",
1060
+ "transformer.h.68.self_attention.query_key_value.SCB": "pytorch_model-00018-of-00019.bin",
1061
+ "transformer.h.68.self_attention.query_key_value.bias": "pytorch_model-00018-of-00019.bin",
1062
+ "transformer.h.68.self_attention.query_key_value.weight": "pytorch_model-00018-of-00019.bin",
1063
+ "transformer.h.69.input_layernorm.bias": "pytorch_model-00018-of-00019.bin",
1064
+ "transformer.h.69.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
1065
+ "transformer.h.69.mlp.dense_4h_to_h.SCB": "pytorch_model-00019-of-00019.bin",
1066
+ "transformer.h.69.mlp.dense_4h_to_h.bias": "pytorch_model-00019-of-00019.bin",
1067
+ "transformer.h.69.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00019.bin",
1068
+ "transformer.h.69.mlp.dense_h_to_4h.SCB": "pytorch_model-00019-of-00019.bin",
1069
+ "transformer.h.69.mlp.dense_h_to_4h.bias": "pytorch_model-00019-of-00019.bin",
1070
+ "transformer.h.69.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00019.bin",
1071
+ "transformer.h.69.post_attention_layernorm.bias": "pytorch_model-00019-of-00019.bin",
1072
+ "transformer.h.69.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin",
1073
+ "transformer.h.69.self_attention.dense.SCB": "pytorch_model-00019-of-00019.bin",
1074
+ "transformer.h.69.self_attention.dense.bias": "pytorch_model-00019-of-00019.bin",
1075
+ "transformer.h.69.self_attention.dense.weight": "pytorch_model-00019-of-00019.bin",
1076
+ "transformer.h.69.self_attention.query_key_value.SCB": "pytorch_model-00019-of-00019.bin",
1077
+ "transformer.h.69.self_attention.query_key_value.bias": "pytorch_model-00019-of-00019.bin",
1078
+ "transformer.h.69.self_attention.query_key_value.weight": "pytorch_model-00019-of-00019.bin",
1079
+ "transformer.h.7.input_layernorm.bias": "pytorch_model-00003-of-00019.bin",
1080
+ "transformer.h.7.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
1081
+ "transformer.h.7.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00019.bin",
1082
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00019.bin",
1083
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00019.bin",
1084
+ "transformer.h.7.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00019.bin",
1085
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00019.bin",
1086
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00019.bin",
1087
+ "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00003-of-00019.bin",
1088
+ "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
1089
+ "transformer.h.7.self_attention.dense.SCB": "pytorch_model-00003-of-00019.bin",
1090
+ "transformer.h.7.self_attention.dense.bias": "pytorch_model-00003-of-00019.bin",
1091
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00003-of-00019.bin",
1092
+ "transformer.h.7.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00019.bin",
1093
+ "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00003-of-00019.bin",
1094
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00003-of-00019.bin",
1095
+ "transformer.h.8.input_layernorm.bias": "pytorch_model-00003-of-00019.bin",
1096
+ "transformer.h.8.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
1097
+ "transformer.h.8.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00019.bin",
1098
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00019.bin",
1099
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00019.bin",
1100
+ "transformer.h.8.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00019.bin",
1101
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00019.bin",
1102
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00019.bin",
1103
+ "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00003-of-00019.bin",
1104
+ "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
1105
+ "transformer.h.8.self_attention.dense.SCB": "pytorch_model-00003-of-00019.bin",
1106
+ "transformer.h.8.self_attention.dense.bias": "pytorch_model-00003-of-00019.bin",
1107
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00019.bin",
1108
+ "transformer.h.8.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00019.bin",
1109
+ "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00019.bin",
1110
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00019.bin",
1111
+ "transformer.h.9.input_layernorm.bias": "pytorch_model-00003-of-00019.bin",
1112
+ "transformer.h.9.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
1113
+ "transformer.h.9.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00019.bin",
1114
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00019.bin",
1115
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00019.bin",
1116
+ "transformer.h.9.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00019.bin",
1117
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00019.bin",
1118
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00019.bin",
1119
+ "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00019.bin",
1120
+ "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
1121
+ "transformer.h.9.self_attention.dense.SCB": "pytorch_model-00004-of-00019.bin",
1122
+ "transformer.h.9.self_attention.dense.bias": "pytorch_model-00004-of-00019.bin",
1123
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00004-of-00019.bin",
1124
+ "transformer.h.9.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00019.bin",
1125
+ "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00004-of-00019.bin",
1126
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00004-of-00019.bin",
1127
+ "transformer.ln_f.bias": "pytorch_model-00019-of-00019.bin",
1128
+ "transformer.ln_f.weight": "pytorch_model-00019-of-00019.bin",
1129
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00019.bin",
1130
+ "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00019.bin",
1131
+ "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00019.bin"
1132
+ }
1133
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
+ size 14500471
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }