Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/c33de8a827c15bf5d69f.json +38 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7809,3 +7809,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_4a4553dc6cf05a499016+613edded/model.neff fi
|
|
| 7809 |
neuronxcc-2.17.194.0+d312836f/MODULE_d99b22ebf11af720ba50+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7810 |
neuronxcc-2.17.194.0+d312836f/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7811 |
neuronxcc-2.17.194.0+d312836f/MODULE_d940b43da508034d0efd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7809 |
neuronxcc-2.17.194.0+d312836f/MODULE_d99b22ebf11af720ba50+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7810 |
neuronxcc-2.17.194.0+d312836f/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7811 |
neuronxcc-2.17.194.0+d312836f/MODULE_d940b43da508034d0efd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7812 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7813 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/c33de8a827c15bf5d69f.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-7B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast_type": "bf16",
|
| 18 |
+
"batch_size": 32,
|
| 19 |
+
"checkpoint_id": "Qwen/Qwen2.5-7B-Instruct",
|
| 20 |
+
"checkpoint_revision": "a09a35458c702b33eeacc393d103063234e8bc28",
|
| 21 |
+
"compiler_type": "neuronx-cc",
|
| 22 |
+
"compiler_version": "2.17.194.0+d312836f",
|
| 23 |
+
"num_cores": 8,
|
| 24 |
+
"sequence_length": 4096,
|
| 25 |
+
"task": "text-generation"
|
| 26 |
+
},
|
| 27 |
+
"num_attention_heads": 28,
|
| 28 |
+
"num_hidden_layers": 28,
|
| 29 |
+
"num_key_value_heads": 4,
|
| 30 |
+
"rms_norm_eps": 1e-06,
|
| 31 |
+
"rope_scaling": null,
|
| 32 |
+
"rope_theta": 1000000.0,
|
| 33 |
+
"sliding_window": 131072,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 152064
|
| 38 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+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_56e0bcfaa3e501d261c0+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aa5933db13574613fe4b68d10d1d20d5f29bc9815ae526f2143f1bc99d533dd
|
| 3 |
+
size 445805
|
neuronxcc-2.17.194.0+d312836f/MODULE_56e0bcfaa3e501d261c0+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f565f5887361dc4c2efc6c81a2dc6ed8cd8460f6504f80eeba04b7aa263972
|
| 3 |
+
size 29789184
|
neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+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_bcf7d640412dc3dcfabe+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04bc2028848a8216166da1fba2b42b3b4c6d3ca36f33b0993b12190d0901437a
|
| 3 |
+
size 355220
|
neuronxcc-2.17.194.0+d312836f/MODULE_bcf7d640412dc3dcfabe+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f09fdc2daafb1718a08768d0e5a1c991def3e565e0eaf73c3b6f1dfbfad4cc98
|
| 3 |
+
size 5407744
|