Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/e26667b714e642d0771d.json +39 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7817,3 +7817,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_304ecf9adecd6c86e472+613edded/model.neff fi
|
|
| 7817 |
neuronxcc-2.17.194.0+d312836f/MODULE_e2da9d6c5d2c3178820a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7818 |
neuronxcc-2.17.194.0+d312836f/MODULE_71d5e7da725f4e5882ab+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7819 |
neuronxcc-2.17.194.0+d312836f/MODULE_abbb692a4a79100862d5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7817 |
neuronxcc-2.17.194.0+d312836f/MODULE_e2da9d6c5d2c3178820a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7818 |
neuronxcc-2.17.194.0+d312836f/MODULE_71d5e7da725f4e5882ab+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7819 |
neuronxcc-2.17.194.0+d312836f/MODULE_abbb692a4a79100862d5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7820 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7821 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/e26667b714e642d0771d.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
|
| 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": 131072,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast_type": "bf16",
|
| 18 |
+
"batch_size": 1,
|
| 19 |
+
"checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
|
| 20 |
+
"checkpoint_revision": "916b56a44061fd5cd7d6a8fb632557ed4f724f60",
|
| 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": 10000,
|
| 33 |
+
"sliding_window": 4096,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"use_mrope": false,
|
| 37 |
+
"use_sliding_window": false,
|
| 38 |
+
"vocab_size": 152064
|
| 39 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+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_43363c464c0295332dab+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fba2dc46923ba083a29c0c9c505e25472f7478d10162982bea1710f03c6b06b
|
| 3 |
+
size 405796
|
neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2b4c375e65bd40e1a037571047b203c08637a32e73ec48bb6b7648d5bf6f41e
|
| 3 |
+
size 29553664
|
neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+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_cb520db271bea6789cc5+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a9e0f97f110efdd7abd9c009c08797d7da3d765f1934f543ca1bfbb686f9054
|
| 3 |
+
size 327365
|
neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e7cbd1d7c09163bf70a184e38ff0d022ab9789f3357c82d435192d50d5ad9e8
|
| 3 |
+
size 2479104
|