Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/phi3/microsoft/phi-4/7e9bce30fa4577df5c63.json +41 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7749,3 +7749,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_5f194d47737258040d3c+613edded/model.neff fi
|
|
| 7749 |
neuronxcc-2.17.194.0+d312836f/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7750 |
neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7751 |
neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7749 |
neuronxcc-2.17.194.0+d312836f/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7750 |
neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7751 |
neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7752 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7753 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/phi3/microsoft/phi-4/7e9bce30fa4577df5c63.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/phi-4",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 5120,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 17920,
|
| 15 |
+
"max_position_embeddings": 16384,
|
| 16 |
+
"model_type": "phi3",
|
| 17 |
+
"neuron": {
|
| 18 |
+
"auto_cast_type": "bf16",
|
| 19 |
+
"batch_size": 1,
|
| 20 |
+
"checkpoint_id": "microsoft/phi-4",
|
| 21 |
+
"checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61",
|
| 22 |
+
"compiler_type": "neuronx-cc",
|
| 23 |
+
"compiler_version": "2.17.194.0+d312836f",
|
| 24 |
+
"num_cores": 10,
|
| 25 |
+
"sequence_length": 4096,
|
| 26 |
+
"task": "text-generation"
|
| 27 |
+
},
|
| 28 |
+
"num_attention_heads": 40,
|
| 29 |
+
"num_hidden_layers": 40,
|
| 30 |
+
"num_key_value_heads": 10,
|
| 31 |
+
"original_max_position_embeddings": 16384,
|
| 32 |
+
"partial_rotary_factor": 1.0,
|
| 33 |
+
"resid_pdrop": 0.0,
|
| 34 |
+
"rms_norm_eps": 1e-05,
|
| 35 |
+
"rope_scaling": null,
|
| 36 |
+
"rope_theta": 250000,
|
| 37 |
+
"sliding_window": null,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 100352
|
| 41 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27cbd6a3e6489625a93e9a2f1bb542a546db0be0acd0ceb9b3ae85b767cf5036
|
| 3 |
+
size 320252
|
neuronxcc-2.17.194.0+d312836f/MODULE_2a10c038669fa2d343e1+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f9a627755304843cdb8342bc705854e774c61ecadfbaba37c9a1fb24d511a97
|
| 3 |
+
size 2540544
|
neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:937d4e3f354a5e172224bb36132c3b6dbfa1e65e3aa0b0a6c301910b7909d84d
|
| 3 |
+
size 414109
|
neuronxcc-2.17.194.0+d312836f/MODULE_ceb1532721b05ed70905+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:263a5c121656de92a3e3df94233b899511841f547a7ed347212c211e71d4e881
|
| 3 |
+
size 4004864
|