Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
276
jburtoft commited on
Commit
dbd9cad
•
1 Parent(s): b267896

Synchronizing local compiler cache.

Browse files
Files changed (22) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/Snowflake/snowflake-arctic-embed-l/ad62c560530518a4523f.json +1 -0
  3. neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/TaylorAI/bge-micro-v2/1384aee4e828bcd1c687.json +1 -0
  4. neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/TaylorAI/bge-micro-v2/fb5aa8e68ce47badf8db.json +1 -0
  5. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/config.json +58 -0
  6. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/model.neuron +3 -0
  7. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/special_tokens_map.json +44 -0
  8. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/tokenizer.json +0 -0
  9. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/tokenizer_config.json +71 -0
  10. neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/vocab.txt +0 -0
  11. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/config.json +50 -0
  12. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/model.neuron +3 -0
  13. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/special_tokens_map.json +37 -0
  14. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/tokenizer.json +0 -0
  15. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/tokenizer_config.json +62 -0
  16. neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/vocab.txt +0 -0
  17. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/config.json +58 -0
  18. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/model.neuron +3 -0
  19. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/special_tokens_map.json +44 -0
  20. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/tokenizer.json +0 -0
  21. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/tokenizer_config.json +71 -0
  22. neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/vocab.txt +0 -0
.gitattributes CHANGED
@@ -6447,3 +6447,6 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_cdc14e51d8d28a61d202+39f12043/model.neff fi
6447
  neuronxcc-2.15.143.0+e39249ad/MODULE_e46e7cf77becae9009a2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6448
  neuronxcc-2.15.143.0+e39249ad/MODULE_e9793fe7a8c6f39badef+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6449
  neuronxcc-2.15.143.0+e39249ad/MODULE_fbfe999e7918c5e3c314+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
6447
  neuronxcc-2.15.143.0+e39249ad/MODULE_e46e7cf77becae9009a2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6448
  neuronxcc-2.15.143.0+e39249ad/MODULE_e9793fe7a8c6f39badef+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6449
  neuronxcc-2.15.143.0+e39249ad/MODULE_fbfe999e7918c5e3c314+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6450
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/model.neuron filter=lfs diff=lfs merge=lfs -text
6451
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/model.neuron filter=lfs diff=lfs merge=lfs -text
6452
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/model.neuron filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/Snowflake/snowflake-arctic-embed-l/ad62c560530518a4523f.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "export_model_type": "transformer", "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 512}, "num_attention_heads": 16, "num_hidden_layers": 24, "position_embedding_type": "absolute", "task": "feature-extraction", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/TaylorAI/bge-micro-v2/1384aee4e828bcd1c687.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "export_model_type": "transformer", "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 384, "id2label": {"0": "LABEL_0"}, "initializer_range": 0.02, "intermediate_size": 1536, "label2id": {"LABEL_0": 0}, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 256, "static_sequence_length": 512}, "num_attention_heads": 12, "num_hidden_layers": 3, "position_embedding_type": "absolute", "task": "feature-extraction", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bert/TaylorAI/bge-micro-v2/fb5aa8e68ce47badf8db.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "export_model_type": "transformer", "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 384, "id2label": {"0": "LABEL_0"}, "initializer_range": 0.02, "intermediate_size": 1536, "label2id": {"LABEL_0": 0}, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_sequence_length": 512}, "num_attention_heads": 12, "num_hidden_layers": 3, "position_embedding_type": "absolute", "task": "feature-extraction", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TaylorAI/bge-micro-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "export_model_type": "transformer",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "neuron": {
24
+ "auto_cast": null,
25
+ "auto_cast_type": null,
26
+ "compiler_type": "neuronx-cc",
27
+ "compiler_version": "2.15.128.0+56dc5a86",
28
+ "disable_fallback": false,
29
+ "disable_fast_relayout": false,
30
+ "dynamic_batch_size": false,
31
+ "inline_weights_to_neff": true,
32
+ "input_names": [
33
+ "input_ids",
34
+ "attention_mask"
35
+ ],
36
+ "model_type": "transformer",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "token_embeddings",
42
+ "sentence_embedding"
43
+ ],
44
+ "static_batch_size": 256,
45
+ "static_sequence_length": 512
46
+ },
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 3,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "task": "feature-extraction",
52
+ "torch_dtype": "float32",
53
+ "torchscript": true,
54
+ "transformers_version": "4.43.2",
55
+ "type_vocab_size": 2,
56
+ "use_cache": true,
57
+ "vocab_size": 30522
58
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/model.neuron ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7299137ba4362542b724f38ee2459429bebf158b1521d8e629aa5a30e144498
3
+ size 77092474
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "max_length": 512,
57
+ "model_max_length": 1000000000000000019884624838656,
58
+ "never_split": null,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "sep_token": "[SEP]",
64
+ "stride": 0,
65
+ "strip_accents": null,
66
+ "tokenize_chinese_chars": true,
67
+ "tokenizer_class": "BertTokenizer",
68
+ "truncation_side": "right",
69
+ "truncation_strategy": "longest_first",
70
+ "unk_token": "[UNK]"
71
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Snowflake/snowflake-arctic-embed-l",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "export_model_type": "transformer",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "neuron": {
18
+ "auto_cast": null,
19
+ "auto_cast_type": null,
20
+ "compiler_type": "neuronx-cc",
21
+ "compiler_version": "2.15.128.0+56dc5a86",
22
+ "dynamic_batch_size": false,
23
+ "inline_weights_to_neff": false,
24
+ "input_names": [
25
+ "input_ids",
26
+ "attention_mask"
27
+ ],
28
+ "model_type": "transformer",
29
+ "optlevel": "2",
30
+ "output_attentions": false,
31
+ "output_hidden_states": false,
32
+ "output_names": [
33
+ "token_embeddings",
34
+ "sentence_embedding"
35
+ ],
36
+ "static_batch_size": 1,
37
+ "static_sequence_length": 512
38
+ },
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "task": "feature-extraction",
44
+ "torch_dtype": "float32",
45
+ "torchscript": true,
46
+ "transformers_version": "4.43.2",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/model.neuron ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0f66d85912643394dbebb8d5c81e578520a3e5624589b7b80e8854928fb895
3
+ size 1339128120
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TaylorAI/bge-micro-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "export_model_type": "transformer",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "neuron": {
24
+ "auto_cast": null,
25
+ "auto_cast_type": null,
26
+ "compiler_type": "neuronx-cc",
27
+ "compiler_version": "2.15.128.0+56dc5a86",
28
+ "disable_fallback": false,
29
+ "disable_fast_relayout": false,
30
+ "dynamic_batch_size": false,
31
+ "inline_weights_to_neff": true,
32
+ "input_names": [
33
+ "input_ids",
34
+ "attention_mask"
35
+ ],
36
+ "model_type": "transformer",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "token_embeddings",
42
+ "sentence_embedding"
43
+ ],
44
+ "static_batch_size": 4,
45
+ "static_sequence_length": 512
46
+ },
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 3,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "task": "feature-extraction",
52
+ "torch_dtype": "float32",
53
+ "torchscript": true,
54
+ "transformers_version": "4.43.2",
55
+ "type_vocab_size": 2,
56
+ "use_cache": true,
57
+ "vocab_size": 30522
58
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/model.neuron ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46524d23c22c3d7d8a6350af2b530418a8f12c75b21848b6feda9e2dd2e00f2e
3
+ size 44570234
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "max_length": 512,
57
+ "model_max_length": 1000000000000000019884624838656,
58
+ "never_split": null,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "sep_token": "[SEP]",
64
+ "stride": 0,
65
+ "strip_accents": null,
66
+ "tokenize_chinese_chars": true,
67
+ "tokenizer_class": "BertTokenizer",
68
+ "truncation_side": "right",
69
+ "truncation_strategy": "longest_first",
70
+ "unk_token": "[UNK]"
71
+ }
neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/vocab.txt ADDED
The diff for this file is too large to render. See raw diff