Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
optimum-internal-testing-user commited on
Commit
b5f34d2
·
verified ·
1 Parent(s): e72d366

Synchronizing local compiler cache.

Browse files
Files changed (23) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/728dd36ae501dabaa50d.json +134 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.hlo_module.pb +1 -1
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.neff +1 -1
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_47040a4f0bf48fd29c51+ed72d204/model.hlo_module.pb +1 -1
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_47040a4f0bf48fd29c51+ed72d204/model.neff +1 -1
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b7172cc10110a470457+ed72d204/model.hlo_module.pb +1 -1
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b7172cc10110a470457+ed72d204/model.neff +1 -1
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6a4730946575bae38107+a9d440f5/model.neff +1 -1
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6a4730946575bae38107+a9d440f5/wrapped_neff.hlo +1 -1
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/model.neff +1 -1
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/wrapped_neff.hlo +1 -1
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9361fb1ac241d0d047f1+a9d440f5/model.neff +1 -1
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9361fb1ac241d0d047f1+a9d440f5/wrapped_neff.hlo +1 -1
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/compile_flags.json +1 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.done +0 -0
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.neff +3 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/compile_flags.json +1 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.done +0 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.hlo_module.pb +3 -0
  22. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.neff +3 -0
  23. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -5076,3 +5076,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6a4730946575bae38107+a9d440f5/wrapped_nef
5076
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5077
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5078
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
5076
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5077
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5078
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5079
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5080
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5081
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/728dd36ae501dabaa50d.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "HuggingFaceTB/SmolLM3-3B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "SmolLM3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "neuron": {
57
+ "_serialized_key": "NxDNeuronConfig",
58
+ "batch_size": 4,
59
+ "capacity_factor": null,
60
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
61
+ "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
62
+ "continuous_batching": true,
63
+ "enable_bucketing": false,
64
+ "ep_degree": 1,
65
+ "fused_qkv": true,
66
+ "glu_mlp": true,
67
+ "local_ranks_size": 2,
68
+ "max_batch_size": 4,
69
+ "max_context_length": 4096,
70
+ "max_topk": 256,
71
+ "n_active_tokens": 4096,
72
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
73
+ "on_device_sampling": true,
74
+ "optimum_neuron_version": "0.4.0.dev0",
75
+ "output_logits": false,
76
+ "pp_degree": 1,
77
+ "sequence_length": 4096,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": "trn1",
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2
83
+ },
84
+ "no_rope_layer_interval": 4,
85
+ "no_rope_layers": [
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 0,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 0,
94
+ 1,
95
+ 1,
96
+ 1,
97
+ 0,
98
+ 1,
99
+ 1,
100
+ 1,
101
+ 0,
102
+ 1,
103
+ 1,
104
+ 1,
105
+ 0,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 0,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 0,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 0,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 0
122
+ ],
123
+ "num_attention_heads": 16,
124
+ "num_hidden_layers": 36,
125
+ "num_key_value_heads": 4,
126
+ "pretraining_tp": 2,
127
+ "rms_norm_eps": 1e-06,
128
+ "rope_scaling": null,
129
+ "rope_theta": 5000000.0,
130
+ "sliding_window": null,
131
+ "use_cache": false,
132
+ "use_sliding_window": false,
133
+ "vocab_size": 128256
134
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8922700fb4e60a2e6978e4d2883589dc852fd97d0f094397a4f53d17368b67fe
3
  size 865460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ab4fc5f3da63f24e78bae11567eb02586de6871f44501149b793bba8ad12e9
3
  size 865460
neuronxcc-2.21.18209.0+043b1bf7/MODULE_19285e519732111e1cab+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdd3eded02ff8286d9c3963f86ec95d5b17b3b2175dde426317556c4a495fbea
3
  size 36148224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b7ec11d4e950f29fbb1d402e0fb47de92d971f7e9bd3da94eed32a7531149e
3
  size 36148224
neuronxcc-2.21.18209.0+043b1bf7/MODULE_47040a4f0bf48fd29c51+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cac0687feb6723e9fe92e18ca3405c084f92a4864a5a356ce34f80a0c71201a2
3
  size 923430
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42afec99775e6c84e8b9a7acbb37638809fd8f17f1e966bb6aa8992232740a2a
3
  size 923430
neuronxcc-2.21.18209.0+043b1bf7/MODULE_47040a4f0bf48fd29c51+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e09a7424ef0e28832257d35f3dca7e5ff47a8ae4ffda7d96b86bff0e86a695a
3
  size 5213184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842fbd53cc1579778273f08a3789d50a2ccddb6e0693eb87bb6d15bee807bde8
3
  size 5213184
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b7172cc10110a470457+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:beca9d97bb0817762268910bf4fd6905bc965bbb31b925f7439c5367afef4ca6
3
  size 1050679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e44bfe923734a9e692c83a3f6f8bf4e15fc148249c77d1aef3fde47ff55a5d1
3
  size 1050679
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b7172cc10110a470457+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb05cd48def23ceeaca42558677439b509041cd6d8f491f4c42a5f28097ad070
3
  size 5827584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28886991d12741447b30efa8893e0977fe2de2c7d53584535b6c26f97bc50df
3
  size 5827584
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6a4730946575bae38107+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f44ddc60439388697a0406229b3520c62c15630f982dc2dc9f1384b916452e38
3
  size 12411904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ec2c1618b220063f382e554a8dedeb5bba4237c24cea8c0332531a7914f769
3
  size 12411904
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6a4730946575bae38107+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11ee2f9841be59bdd1f148fe2a72c7c9e4a38692e5381fba22fa2604bd758565
3
  size 12559063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b058d2acbfa23a6a8e6c047aeeaf38880f13930bab33f23dca11f747e79a6d
3
  size 12559063
neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e31c48184928f8bfdb946f4e49e2990fa2589b8cadbac84ca942503177b9b61
3
  size 3503104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b9c96dcc31df06f6701cc67c7203813ed25e1d916ae3e97df5ef450bb599ec
3
  size 3503104
neuronxcc-2.21.18209.0+043b1bf7/MODULE_75b1e776b16b9953c241+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f67ed60e446374d3253b40700ba31bb11483e9d64b07fb2007eb9209b68869ee
3
  size 3640300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1809f7c5a1b20cd8d5348bd72a021ab8e38bb910437761bc32b3c27b116b976
3
  size 3640300
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9361fb1ac241d0d047f1+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3742b6d8468bdafeb2688cd11636fd0bd17d5ca2ca200846f9580dc57a43eed6
3
  size 6974464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94268e27a81f1ee6de2f8082852f047b480ebd477a491c886d40b594c26b385
3
  size 6974464
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9361fb1ac241d0d047f1+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4fb76c9ca9ec7d660f35c08ab1ffb356bec8c6c9971e884d30305abeac309cb
3
  size 7158800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc1719e07caf3b44da4a897ec365164231cb566c062d8c7a3a02bef630183db
3
  size 7158800
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24a5d719ee434ba7055d6d557ab7b4fe7c4a289958bb68e0ee858c9f9f2f38f
3
+ size 1061093
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb2e1a0c8bca180c3d7d+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba36a0a0c02fed08f16bb0544c0cc49b227038a4a16f2350a8543d6742a7862e
3
+ size 9473024
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25ade0a3f52e4ef283ba2768a1420e559bb8c5c6ab4b261c432d72a52fc9e6d
3
+ size 863510
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997fdae009c54f5993d547fe5dcc5df5b20cc14fab9ae500ee6526c9d844a283
3
+ size 6769664
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4fc6de37faaa9d9cd07708780e653fe6e24dac6107103d9911d199aa723494
3
+ size 6936331