Jingya HF staff commited on
Commit
9fb6c9d
1 Parent(s): b6c0960

upload model

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ model.neuron filter=lfs diff=lfs merge=lfs -text
all_metrics.csv ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ timestamp,run_id,name,subgraph,scope,sub_scope,value,unit,
2
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,CanonicalizeIR,0.0093994140625,Seconds
3
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ExpandBatchNorm,0.009254693984985352,Seconds
4
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ResolveComplicatePredicates,0.0071446895599365234,Seconds
5
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,AffinePredicateResolution,0.008615255355834961,Seconds
6
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,EliminateDivs,0.00906991958618164,Seconds
7
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TensorOpFusion,0.009348154067993164,Seconds
8
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TensorOpTransform,0.034893035888671875,Seconds
9
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LowerTensorOp,0.011458396911621094,Seconds
10
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,MemcpyElimination,0.8764715194702148,Seconds
11
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DeadStoreElimination,0.6812219619750977,Seconds
12
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SimplifySlice,0.0030181407928466797,Seconds
13
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,PadElimination,0.0003688335418701172,Seconds
14
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LoopFusion,0.37325453758239746,Seconds
15
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ValueNumbering,0.0283353328704834,Seconds
16
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TCTransform,0.017099857330322266,Seconds
17
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,CommuteConcat,0.010370254516601562,Seconds
18
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,RecognizeOpIdiom,0.015559911727905273,Seconds
19
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,MaskPropagation,0.011378765106201172,Seconds
20
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,Recompute,0.0005948543548583984,Seconds
21
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DoNothing,9.083747863769531e-05,Seconds
22
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,MutateDataType,0.0023496150970458984,Seconds
23
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,AutoCastTCInputs,0.003918647766113281,Seconds
24
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,GenericAccessSimplifier,0.01243281364440918,Seconds
25
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,Simplifier,0.41060328483581543,Seconds
26
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,Delinearization,0.03841114044189453,Seconds
27
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DelinearIndices,0.015451431274414062,Seconds
28
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DeadCodeElimination,0.007534027099609375,Seconds
29
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizeCCOpLayout,0.003658771514892578,Seconds
30
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,InferIntrinsicOnCC,0.050520896911621094,Seconds
31
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ResolveAccessConflict,0.02746438980102539,Seconds
32
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LocalLayoutOpt,0.023167848587036133,Seconds
33
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,GlobalLayoutOpt,0.3492927551269531,Seconds
34
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,CanonicalizeDAG,0.007649421691894531,Seconds
35
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,FlattenAxesForTiling,0.008371829986572266,Seconds
36
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SundaSizeTiling,0.44942784309387207,Seconds
37
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,InferTongaTensor,0.1616523265838623,Seconds
38
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,RewriteReplicationMatmul,0.007273435592651367,Seconds
39
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DataLocalityOpt,1.1143321990966797,Seconds
40
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TilingProfiler,0.009297370910644531,Seconds
41
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizeSundaMacro,0.022243261337280273,Seconds
42
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,PerfectLoopNest,0.016142606735229492,Seconds
43
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,RewriteWeights,0.23421001434326172,Seconds
44
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ReshapeWeights,0.004595518112182617,Seconds
45
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,FlattenMacroLoop,0.06238913536071777,Seconds
46
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SimplifyPredicates,0.22608160972595215,Seconds
47
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,InferInitValue,0.7848811149597168,Seconds
48
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaSimplifier,0.06940984725952148,Seconds
49
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SimplifyTensor,0.03229641914367676,Seconds
50
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LICM,0.10033583641052246,Seconds
51
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SundaISel,0.19430756568908691,Seconds
52
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaLoopFusion,0.08935689926147461,Seconds
53
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,FactorizeBlkDims,0.03960418701171875,Seconds
54
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaValueNumbering,0.02214527130126953,Seconds
55
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaInstComb,0.2443535327911377,Seconds
56
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,VectorizeMatMult,0.002829313278198242,Seconds
57
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,VectorizeDMA,0.017197132110595703,Seconds
58
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizePartitionReduce,0.0033822059631347656,Seconds
59
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,PartialLoopFusion,0.08432555198669434,Seconds
60
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LowerTranspose,0.037595510482788086,Seconds
61
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LateTongaInstComb,0.16178202629089355,Seconds
62
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LowerTongaBatchId,0.002024412155151367,Seconds
63
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SplitAccGrp,0.003551006317138672,Seconds
64
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SpillPSum,0.034529685974121094,Seconds
65
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaLICM,0.03946352005004883,Seconds
66
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,InferPSumTensor,0.09653544425964355,Seconds
67
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,WeightCoalescing,0.014181375503540039,Seconds
68
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LowerIntrinsics,0.0035042762756347656,Seconds
69
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizeSundaAccess,0.02397894859313965,Seconds
70
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaAffineLoopXform,0.013040304183959961,Seconds
71
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,VectorizeAllReduce,0.003997087478637695,Seconds
72
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,RelaxPredicates,0.007230043411254883,Seconds
73
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TensorInitialization,0.00619816780090332,Seconds
74
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,TongaSimplifyPredicates,0.012606382369995117,Seconds
75
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,ExpandISAMacro,0.005366325378417969,Seconds
76
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizeType,0.009764671325683594,Seconds
77
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SimplifyTongaTensor,0.011408090591430664,Seconds
78
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DMALocalityOpt,0.0025980472564697266,Seconds
79
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DataStreaming,0.009914875030517578,Seconds
80
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,PSUMModuloAlloc,0.2481861114501953,Seconds
81
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,LegalizeStreamShuffle,0.004734516143798828,Seconds
82
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,CoalesceCCOp,0.003985881805419922,Seconds
83
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SimpleAllReduceTiling,0.004281520843505859,Seconds
84
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,StaticProfiler,0.015914201736450195,Seconds
85
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SplitAPUnionSets,0.05818510055541992,Seconds
86
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,SundaLowerGenericAccess,0.0043087005615234375,Seconds
87
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,DumpGraphAndMetadata,0.011687755584716797,Seconds
88
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg0000,Tensorizer,BirCodeGenLoop,0.11950278282165527,Seconds
89
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,root,Tensorizer,All,9.188081979751587,Seconds
90
+ ,all-MiniLM-L6-v2-neuronx,TPBCount,None,KELP,None,1,Count
91
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,root,Frontend,0,9.660834789276123,Seconds
92
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,all,Frontend,0,9.664303064346313,Seconds
93
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg00,HHChecker,0,1.2636184692382812e-05,Seconds
94
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,all,HHChecker,0,0.003728151321411133,Seconds
95
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,sg00,WalrusDriver,0,0.3347148895263672,Seconds
96
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,all,WalrusDriver,0,0.34115004539489746,Seconds
97
+ ,all-MiniLM-L6-v2-neuronx,EstimatedLowerBoundLatency,None,KELP,None,0,Milliseconds
98
+ ,all-MiniLM-L6-v2-neuronx,EstimatedUpperBoundThroughput,None,KELP,None,0,Count/Second
99
+ ,all-MiniLM-L6-v2-neuronx,InferentiaDRAMUsage,None,KELP,None,0,Bytes
100
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,all,Kelper,0,3.2928266525268555,Seconds
101
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,root,Pipeline,0,13.31865906715393,Seconds
102
+ ,all-MiniLM-L6-v2-neuronx,CompilationTime,all,production_total,None,13.302007913589478,Seconds
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_cast": null,
8
+ "auto_cast_type": null,
9
+ "classifier_dropout": null,
10
+ "dynamic_batch_size": true,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 384,
15
+ "initializer_range": 0.02,
16
+ "input_names": [
17
+ "input_ids",
18
+ "attention_mask",
19
+ "token_type_ids"
20
+ ],
21
+ "intermediate_size": 1536,
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "neuron_batch_size": 1,
26
+ "neuron_sequence_length": 128,
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 6,
29
+ "output_names": [
30
+ "last_hidden_state",
31
+ "pooler_output"
32
+ ],
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "torchscript": true,
36
+ "transformers_version": "4.29.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
model.neuron ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3594009167a9f92e05f76b8415348a850b2d6427a340867ba840a9ebc0a4bbdb
3
+ size 83573752
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff