Synchronizing local compiler cache.
Browse files- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json +165 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.hlo_module.pb +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.hlo_module.pb +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo +1 -1
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"prefill_chunk_size": 0,
|
| 43 |
+
"sequence_length": 1024,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": "trn1",
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": {
|
| 58 |
+
"long_factor": [
|
| 59 |
+
1.0800000429153442,
|
| 60 |
+
1.1100000143051147,
|
| 61 |
+
1.1399999856948853,
|
| 62 |
+
1.340000033378601,
|
| 63 |
+
1.5899999141693115,
|
| 64 |
+
1.600000023841858,
|
| 65 |
+
1.6200000047683716,
|
| 66 |
+
2.620000123977661,
|
| 67 |
+
3.2300000190734863,
|
| 68 |
+
3.2300000190734863,
|
| 69 |
+
4.789999961853027,
|
| 70 |
+
7.400000095367432,
|
| 71 |
+
7.700000286102295,
|
| 72 |
+
9.09000015258789,
|
| 73 |
+
12.199999809265137,
|
| 74 |
+
17.670000076293945,
|
| 75 |
+
24.46000099182129,
|
| 76 |
+
28.57000160217285,
|
| 77 |
+
30.420001983642578,
|
| 78 |
+
30.840002059936523,
|
| 79 |
+
32.590003967285156,
|
| 80 |
+
32.93000411987305,
|
| 81 |
+
42.320003509521484,
|
| 82 |
+
44.96000289916992,
|
| 83 |
+
50.340003967285156,
|
| 84 |
+
50.45000457763672,
|
| 85 |
+
57.55000305175781,
|
| 86 |
+
57.93000411987305,
|
| 87 |
+
58.21000289916992,
|
| 88 |
+
60.1400032043457,
|
| 89 |
+
62.61000442504883,
|
| 90 |
+
62.62000274658203,
|
| 91 |
+
62.71000289916992,
|
| 92 |
+
63.1400032043457,
|
| 93 |
+
63.1400032043457,
|
| 94 |
+
63.77000427246094,
|
| 95 |
+
63.93000411987305,
|
| 96 |
+
63.96000289916992,
|
| 97 |
+
63.970001220703125,
|
| 98 |
+
64.02999877929688,
|
| 99 |
+
64.06999969482422,
|
| 100 |
+
64.08000183105469,
|
| 101 |
+
64.12000274658203,
|
| 102 |
+
64.41000366210938,
|
| 103 |
+
64.4800033569336,
|
| 104 |
+
64.51000213623047,
|
| 105 |
+
64.52999877929688,
|
| 106 |
+
64.83999633789062
|
| 107 |
+
],
|
| 108 |
+
"short_factor": [
|
| 109 |
+
1.0,
|
| 110 |
+
1.0199999809265137,
|
| 111 |
+
1.0299999713897705,
|
| 112 |
+
1.0299999713897705,
|
| 113 |
+
1.0499999523162842,
|
| 114 |
+
1.0499999523162842,
|
| 115 |
+
1.0499999523162842,
|
| 116 |
+
1.0499999523162842,
|
| 117 |
+
1.0499999523162842,
|
| 118 |
+
1.0699999332427979,
|
| 119 |
+
1.0999999046325684,
|
| 120 |
+
1.1099998950958252,
|
| 121 |
+
1.1599998474121094,
|
| 122 |
+
1.1599998474121094,
|
| 123 |
+
1.1699998378753662,
|
| 124 |
+
1.2899998426437378,
|
| 125 |
+
1.339999794960022,
|
| 126 |
+
1.679999828338623,
|
| 127 |
+
1.7899998426437378,
|
| 128 |
+
1.8199998140335083,
|
| 129 |
+
1.8499997854232788,
|
| 130 |
+
1.8799997568130493,
|
| 131 |
+
1.9099997282028198,
|
| 132 |
+
1.9399996995925903,
|
| 133 |
+
1.9899996519088745,
|
| 134 |
+
2.0199997425079346,
|
| 135 |
+
2.0199997425079346,
|
| 136 |
+
2.0199997425079346,
|
| 137 |
+
2.0199997425079346,
|
| 138 |
+
2.0199997425079346,
|
| 139 |
+
2.0199997425079346,
|
| 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 |
+
2.0299997329711914,
|
| 149 |
+
2.0799996852874756,
|
| 150 |
+
2.0899996757507324,
|
| 151 |
+
2.189999580383301,
|
| 152 |
+
2.2199995517730713,
|
| 153 |
+
2.5899994373321533,
|
| 154 |
+
2.729999542236328,
|
| 155 |
+
2.749999523162842,
|
| 156 |
+
2.8399994373321533
|
| 157 |
+
],
|
| 158 |
+
"type": "longrope"
|
| 159 |
+
},
|
| 160 |
+
"rope_theta": 10000.0,
|
| 161 |
+
"sliding_window": 262144,
|
| 162 |
+
"tie_word_embeddings": false,
|
| 163 |
+
"use_cache": true,
|
| 164 |
+
"vocab_size": 32064
|
| 165 |
+
}
|
neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19467264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b61afe9ca0fd8388e61b58cd10018a3f20964d6c1cc9129a51158c91f704f7c
|
| 3 |
size 19467264
|
neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5284864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34483322f76260cff8dc8177b6f292d92de2657488925862a42fb723f7763d6e
|
| 3 |
size 5284864
|
neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5470443
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb10ad9a01509ee69bf28a6225c22464240fa4a0da99ef84e016d07112ce833
|
| 3 |
size 5470443
|
neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6104064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98a5f12d931f1a96ed76bf68a2f47b6d7aee72b5e179418b0a2614b904d517bd
|
| 3 |
size 6104064
|
neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6289083
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf63bf8cfb8fdbdfbb32ce75fe08c3824b2becd335167f9f94803928b354e4e3
|
| 3 |
size 6289083
|
neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 123423744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f4acc676e3eae27cc4d41a06fc5f8749937b1df4dab03839d88e94e7a52dbd
|
| 3 |
size 123423744
|
neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 766575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b8b1bce84f04c19a9e85f0766507030cb5a3ea768fbda4ae5652066d623bb20
|
| 3 |
size 766575
|
neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27065344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b165787bfcb8e096f3a2129e39b1acaac2a6e78d21db2c908663b4a3ea5b0238
|
| 3 |
size 27065344
|
neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 773757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d13ee345d91aeda34cc2b9a16e56a4be973f9879d481ccd06da62978a6d23b84
|
| 3 |
size 773757
|
neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7906304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba554e5d12264b42138c4cc4754602b3744fb8cb29495976f51e2504c743fa3a
|
| 3 |
size 7906304
|
neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8053608
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302b6d7f60b1fb7a2f759baf166968751fce1661a3dd51cfc56b021aee9375a1
|
| 3 |
size 8053608
|