Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-14B/0dd1bb4df1da89aabd5d.json +38 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7833,3 +7833,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_4e9ba69c49d3551e2b6a+613edded/model.neff fi
|
|
| 7833 |
neuronxcc-2.17.194.0+d312836f/MODULE_b41edc3f83cd80184989+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7834 |
neuronxcc-2.17.194.0+d312836f/MODULE_87be56d72f74e0727e94+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7835 |
neuronxcc-2.17.194.0+d312836f/MODULE_d96d38302f6e06310c28+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7833 |
neuronxcc-2.17.194.0+d312836f/MODULE_b41edc3f83cd80184989+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7834 |
neuronxcc-2.17.194.0+d312836f/MODULE_87be56d72f74e0727e94+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7835 |
neuronxcc-2.17.194.0+d312836f/MODULE_d96d38302f6e06310c28+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7836 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7837 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+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/Qwen2.5-14B/0dd1bb4df1da89aabd5d.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-14B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 13824,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 48,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast_type": "bf16",
|
| 18 |
+
"batch_size": 1,
|
| 19 |
+
"checkpoint_id": "Qwen/Qwen2.5-14B",
|
| 20 |
+
"checkpoint_revision": "97e1e76335b7017d8f67c08a19d103c0504298c9",
|
| 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": 40,
|
| 28 |
+
"num_hidden_layers": 48,
|
| 29 |
+
"num_key_value_heads": 8,
|
| 30 |
+
"rms_norm_eps": 1e-05,
|
| 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_b68a6be8c019d9e6ccc0+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_b68a6be8c019d9e6ccc0+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc23983cc33471ac49ad349e3a37aa4f4b2ad56ba2fb7d22bc660073c477da4
|
| 3 |
+
size 694839
|
neuronxcc-2.17.194.0+d312836f/MODULE_b68a6be8c019d9e6ccc0+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c63dcaa315a3c4b7fb08b9f5e9c84f7d5e85292a3b150837a1154939b80fe2b
|
| 3 |
+
size 2929664
|
neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+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_eb1ba6256bb5b7f6ee83+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b93264ea67de142ca936abe6f6bd361b1c9fb97ee4b045e80dfeaf30c8cae73f
|
| 3 |
+
size 560492
|
neuronxcc-2.17.194.0+d312836f/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb6aac1ec231294825b04480c6aa67763088d8ab4e69ebbbf310e4c605192bb9
|
| 3 |
+
size 5080064
|