Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-0.5B/d6fa3a9fc1098a5758b7.json +39 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/model.neff +3 -0
.gitattributes
CHANGED
@@ -7821,3 +7821,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_43363c464c0295332dab+613edded/model.neff fi
|
|
7821 |
neuronxcc-2.17.194.0+d312836f/MODULE_cb520db271bea6789cc5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7822 |
neuronxcc-2.17.194.0+d312836f/MODULE_2f5d0dadd623f2b18773+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7823 |
neuronxcc-2.17.194.0+d312836f/MODULE_aef53ca68316ee457163+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
|
7822 |
neuronxcc-2.17.194.0+d312836f/MODULE_2f5d0dadd623f2b18773+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7823 |
neuronxcc-2.17.194.0+d312836f/MODULE_aef53ca68316ee457163+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7824 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
7825 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+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/Qwen2.5-0.5B/d6fa3a9fc1098a5758b7.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"Qwen2ForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4864,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 24,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"neuron": {
|
17 |
+
"auto_cast_type": "bf16",
|
18 |
+
"batch_size": 1,
|
19 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
20 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
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": 14,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"num_key_value_heads": 2,
|
30 |
+
"rms_norm_eps": 1e-06,
|
31 |
+
"rope_scaling": null,
|
32 |
+
"rope_theta": 1000000.0,
|
33 |
+
"sliding_window": 32768,
|
34 |
+
"tie_word_embeddings": true,
|
35 |
+
"use_cache": true,
|
36 |
+
"use_mrope": false,
|
37 |
+
"use_sliding_window": false,
|
38 |
+
"vocab_size": 151936
|
39 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+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_08e3d3755d9db0fe195a+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12c8e43acef9aa527b6d216d9dfe23dd0a85cbf76e06bac2deec585b506c6fdc
|
3 |
+
size 278717
|
neuronxcc-2.17.194.0+d312836f/MODULE_08e3d3755d9db0fe195a+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16f89d41322310bc835a2a1ab385abfac1201f1d17cc4b4f40699b7c19f29007
|
3 |
+
size 994304
|
neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+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_9848c49e5806c7dfaf23+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd6c24c48e664a4638b17ee698fccfa778c1297bb6c42d0834b19aa5dab70d57
|
3 |
+
size 345700
|
neuronxcc-2.17.194.0+d312836f/MODULE_9848c49e5806c7dfaf23+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb692f1c32b9b745c368c5c6d3e616e397ce32dd69a4e69220214456429afe48
|
3 |
+
size 18750464
|