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/b99bab88b5323df2c79e.json +38 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.neff +3 -0
.gitattributes
CHANGED
@@ -7747,3 +7747,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_8b8991d92b27943066fc+613edded/model.neff fi
|
|
7747 |
neuronxcc-2.17.194.0+d312836f/MODULE_e90f5722b4a5608d3821+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7748 |
neuronxcc-2.17.194.0+d312836f/MODULE_5f194d47737258040d3c+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
|
|
|
|
|
|
7747 |
neuronxcc-2.17.194.0+d312836f/MODULE_e90f5722b4a5608d3821+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7748 |
neuronxcc-2.17.194.0+d312836f/MODULE_5f194d47737258040d3c+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
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/b99bab88b5323df2c79e.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": 1,
|
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": 2,
|
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_cc5981296dce23fea50a+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_cc5981296dce23fea50a+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ea1f65f176bb85c477bfd266ecc9b7219d1253fa95876b6970f2fbf3443a825
|
3 |
+
size 327477
|
neuronxcc-2.17.194.0+d312836f/MODULE_cc5981296dce23fea50a+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:756f63160c3d2fa0270169e6fbab6d0cc0d96a1c12eaef338329585f2858d55b
|
3 |
+
size 8213504
|
neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+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_fe7c19e7677d8612ee16+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e1f22cde6140f5207be97e906d00aacecced3e3fbbe10b73c8f83f0b7629fb6
|
3 |
+
size 406132
|
neuronxcc-2.17.194.0+d312836f/MODULE_fe7c19e7677d8612ee16+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4e2e9fddb821e02c521f9e080e3e48913603f627965e1a81e51a7c0023509c0
|
3 |
+
size 7117824
|