Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
optimum-internal-testing-user commited on
Commit
57aa10d
·
verified ·
1 Parent(s): 51b543a

Synchronizing local compiler cache.

Browse files
Files changed (20) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/phi3/microsoft/Phi-3.5-mini-instruct/46e964a86faeb179e2ca.json +164 -0
  3. neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff +1 -1
  4. neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo +1 -1
  5. neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff +1 -1
  6. neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff +1 -1
  7. neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/compile_flags.json +1 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.done +0 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff +1 -1
  13. neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo +1 -1
  14. neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/compile_flags.json +1 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.done +0 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.hlo_module.pb +3 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff +1 -1
  19. neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff +1 -1
  20. neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo +1 -1
.gitattributes CHANGED
@@ -6098,3 +6098,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff
6098
  neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6099
  neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6100
  neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
6098
  neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6099
  neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6100
  neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6101
+ neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6102
+ neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6103
+ neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/phi3/microsoft/Phi-3.5-mini-instruct/46e964a86faeb179e2ca.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "microsoft/Phi-3.5-mini-instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Phi3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {
11
+ "AutoConfig": "configuration_phi3.Phi3Config",
12
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
13
+ },
14
+ "dtype": "bfloat16",
15
+ "embd_pdrop": 0.0,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "max_position_embeddings": 131072,
21
+ "model_type": "phi3",
22
+ "neuron": {
23
+ "_serialized_key": "NxDNeuronConfig",
24
+ "batch_size": 4,
25
+ "capacity_factor": null,
26
+ "checkpoint_id": "microsoft/Phi-3.5-mini-instruct",
27
+ "checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77",
28
+ "continuous_batching": true,
29
+ "ep_degree": 1,
30
+ "fused_qkv": true,
31
+ "glu_mlp": true,
32
+ "local_ranks_size": 2,
33
+ "max_batch_size": 4,
34
+ "max_context_length": 4096,
35
+ "max_topk": 256,
36
+ "n_active_tokens": 4096,
37
+ "neuronxcc_version": "2.21.33363.0+82129205",
38
+ "on_device_sampling": true,
39
+ "optimum_neuron_version": "0.4.4.dev2",
40
+ "output_logits": false,
41
+ "pp_degree": 1,
42
+ "sequence_length": 4096,
43
+ "speculation_length": 0,
44
+ "start_rank_id": 0,
45
+ "target": "trn1",
46
+ "torch_dtype": "bfloat16",
47
+ "tp_degree": 2
48
+ },
49
+ "num_attention_heads": 32,
50
+ "num_hidden_layers": 32,
51
+ "num_key_value_heads": 32,
52
+ "original_max_position_embeddings": 4096,
53
+ "partial_rotary_factor": 1.0,
54
+ "resid_pdrop": 0.0,
55
+ "rms_norm_eps": 1e-05,
56
+ "rope_scaling": {
57
+ "long_factor": [
58
+ 1.0800000429153442,
59
+ 1.1100000143051147,
60
+ 1.1399999856948853,
61
+ 1.340000033378601,
62
+ 1.5899999141693115,
63
+ 1.600000023841858,
64
+ 1.6200000047683716,
65
+ 2.620000123977661,
66
+ 3.2300000190734863,
67
+ 3.2300000190734863,
68
+ 4.789999961853027,
69
+ 7.400000095367432,
70
+ 7.700000286102295,
71
+ 9.09000015258789,
72
+ 12.199999809265137,
73
+ 17.670000076293945,
74
+ 24.46000099182129,
75
+ 28.57000160217285,
76
+ 30.420001983642578,
77
+ 30.840002059936523,
78
+ 32.590003967285156,
79
+ 32.93000411987305,
80
+ 42.320003509521484,
81
+ 44.96000289916992,
82
+ 50.340003967285156,
83
+ 50.45000457763672,
84
+ 57.55000305175781,
85
+ 57.93000411987305,
86
+ 58.21000289916992,
87
+ 60.1400032043457,
88
+ 62.61000442504883,
89
+ 62.62000274658203,
90
+ 62.71000289916992,
91
+ 63.1400032043457,
92
+ 63.1400032043457,
93
+ 63.77000427246094,
94
+ 63.93000411987305,
95
+ 63.96000289916992,
96
+ 63.970001220703125,
97
+ 64.02999877929688,
98
+ 64.06999969482422,
99
+ 64.08000183105469,
100
+ 64.12000274658203,
101
+ 64.41000366210938,
102
+ 64.4800033569336,
103
+ 64.51000213623047,
104
+ 64.52999877929688,
105
+ 64.83999633789062
106
+ ],
107
+ "short_factor": [
108
+ 1.0,
109
+ 1.0199999809265137,
110
+ 1.0299999713897705,
111
+ 1.0299999713897705,
112
+ 1.0499999523162842,
113
+ 1.0499999523162842,
114
+ 1.0499999523162842,
115
+ 1.0499999523162842,
116
+ 1.0499999523162842,
117
+ 1.0699999332427979,
118
+ 1.0999999046325684,
119
+ 1.1099998950958252,
120
+ 1.1599998474121094,
121
+ 1.1599998474121094,
122
+ 1.1699998378753662,
123
+ 1.2899998426437378,
124
+ 1.339999794960022,
125
+ 1.679999828338623,
126
+ 1.7899998426437378,
127
+ 1.8199998140335083,
128
+ 1.8499997854232788,
129
+ 1.8799997568130493,
130
+ 1.9099997282028198,
131
+ 1.9399996995925903,
132
+ 1.9899996519088745,
133
+ 2.0199997425079346,
134
+ 2.0199997425079346,
135
+ 2.0199997425079346,
136
+ 2.0199997425079346,
137
+ 2.0199997425079346,
138
+ 2.0199997425079346,
139
+ 2.0299997329711914,
140
+ 2.0299997329711914,
141
+ 2.0299997329711914,
142
+ 2.0299997329711914,
143
+ 2.0299997329711914,
144
+ 2.0299997329711914,
145
+ 2.0299997329711914,
146
+ 2.0299997329711914,
147
+ 2.0299997329711914,
148
+ 2.0799996852874756,
149
+ 2.0899996757507324,
150
+ 2.189999580383301,
151
+ 2.2199995517730713,
152
+ 2.5899994373321533,
153
+ 2.729999542236328,
154
+ 2.749999523162842,
155
+ 2.8399994373321533
156
+ ],
157
+ "type": "longrope"
158
+ },
159
+ "rope_theta": 10000.0,
160
+ "sliding_window": 262144,
161
+ "tie_word_embeddings": false,
162
+ "use_cache": true,
163
+ "vocab_size": 32064
164
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:352e1f4fa5879bbce960062200136f1973ec4bd426e9b8f640627b514922673d
3
  size 6933504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21f6bbda57bf7e070cdc973f3fa7c2644644fbf240be8541b7065349c8dcef8
3
  size 6933504
neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:488a4589cff192212f11c47d203f5f3d182e50a7b1f35eda5e8da1e15717747c
3
  size 7117697
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10393c2cab5611ae66184955d37e5ee955eb6f40016323dcc12ac2c8d4bcc491
3
  size 7117697
neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d47b2099e1f344db8cd4f2ae01b0eac58d96d14b340a38c9c1ae4ff07ff5939
3
  size 71302144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68389367bb30af25de76a4c417e2d0c446b2562faa97b2cbb36aa2a9256dae0d
3
  size 71302144
neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f8f677cddb6c3b3649824eeaff9c19a705501d084bdb35edd86315ce5aa14ef
3
  size 14654464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8476d85cba12830b772ba3f157a569bb0c2cb2bbfd65c678b90251ba6f06ef5
3
  size 14654464
neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413e24966ec219391e013f4338cbab4c3cd1cebf49080679fa1dc73f26a51196
3
+ size 699875
neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb478847dd694f7ad0a83746a6410c240f0f462c807be9ac4197cd6e22395740
3
+ size 12411904
neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831569ad3797f3f05f180da2720fe57b55a1be452113afc66b7e4ee63b90a894
3
+ size 12558920
neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89dff9420bb47f469d7ea4e14bba33f5206564b8389652e4e96cb42807161cd
3
  size 5008384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d98308e45ddd448ddbc8a54dfab20d673adb007ac2926d05dc406c8b88377fa0
3
  size 5008384
neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:279c14778484f37804d09e1f38b623bd4aa47615e73ab0955fef78270710077c
3
  size 5192563
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e00ca7c5c487cc4686abfa7e8f7ea115e132067590de051fbba1fb9db8d0ad
3
  size 5192563
neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/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/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29f438087c8183891b0a906633385de9ff9254877beef03c4ae441492f5c570
3
+ size 923054
neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a0679a4c53faef93dac15fbb16bfa557f58e1defa538f12df17745ea36b18b
3
+ size 5223424
neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5ce4ad0d118a7625c8e4ac87af76d19f72cd57f0a4e156e36908d4e8f3c83d
3
  size 5827584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfad88dded44abf213ec8d96d06594c888361b6e60c3df2af7cf59eb0b3ad5d
3
  size 5827584
neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8182ac1ce77047e9988d08414cb4d501647ae5e330d05427579ff4809e17c177
3
  size 1721344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f0db943bae305a68c80774a9fe26ed9f803348b9759982bd1bb945756f1787
3
  size 1721344
neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d647b453b48c25e6365291bcc24d360ce075c338a776de1588fefd0681f53ffb
3
  size 1877650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c890850f31c43d590c8728eaa8097b04b52f04486c7c1b77efb67e947a11b328
3
  size 1877650