Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
611
dacorvo HF Staff commited on
Commit
3bf701c
·
verified ·
1 Parent(s): e022f3a

Synchronizing local compiler cache.

Browse files
Files changed (11) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/ddc35ccae8149a68f886.json +133 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/compile_flags.json +1 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.done +0 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.neff +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/compile_flags.json +1 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.done +0 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.neff +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -12304,3 +12304,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_b4752fbda74c3442f3d2+a02c3a36/wrapped_nef
12304
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_05a052c7e55710a3afd0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
12305
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6bf0de930c0aecede513+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12306
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6bf0de930c0aecede513+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
12304
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_05a052c7e55710a3afd0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
12305
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6bf0de930c0aecede513+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12306
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6bf0de930c0aecede513+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12307
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
12308
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12309
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/ddc35ccae8149a68f886.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "HuggingFaceTB/SmolLM3-3B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "SmolLM3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "neuron": {
57
+ "_serialized_key": "NxDNeuronConfig",
58
+ "batch_size": 16,
59
+ "capacity_factor": null,
60
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
61
+ "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
62
+ "continuous_batching": true,
63
+ "ep_degree": 1,
64
+ "fused_qkv": true,
65
+ "glu_mlp": true,
66
+ "local_ranks_size": 2,
67
+ "max_batch_size": 16,
68
+ "max_context_length": 4096,
69
+ "max_topk": 256,
70
+ "n_active_tokens": 4096,
71
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
72
+ "on_device_sampling": true,
73
+ "optimum_neuron_version": "0.4.1.dev0",
74
+ "output_logits": false,
75
+ "pp_degree": 1,
76
+ "sequence_length": 4096,
77
+ "speculation_length": 0,
78
+ "start_rank_id": 0,
79
+ "target": "trn1",
80
+ "torch_dtype": "bfloat16",
81
+ "tp_degree": 2
82
+ },
83
+ "no_rope_layer_interval": 4,
84
+ "no_rope_layers": [
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 0,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 0,
93
+ 1,
94
+ 1,
95
+ 1,
96
+ 0,
97
+ 1,
98
+ 1,
99
+ 1,
100
+ 0,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 0,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 0,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 0,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 0,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 0
121
+ ],
122
+ "num_attention_heads": 16,
123
+ "num_hidden_layers": 36,
124
+ "num_key_value_heads": 4,
125
+ "pretraining_tp": 2,
126
+ "rms_norm_eps": 1e-06,
127
+ "rope_scaling": null,
128
+ "rope_theta": 5000000.0,
129
+ "sliding_window": null,
130
+ "use_cache": false,
131
+ "use_sliding_window": false,
132
+ "vocab_size": 128256
133
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb58a3e9015c133397d7dd6a6a9a041328c1399012de42a395dee9b7cdf5d2bf
3
+ size 1061093
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0382ea154807a8873588+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44289473d417ae05a6ed571df883baf93377d25758d9069591d947bb66f7ff4
3
+ size 9473024
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037c50df4da125a787ac382662170a2b0d655e4c64d057e10597dbeb4b2878b7
3
+ size 863958
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbbd35da08ad98a87c216b18e85e92a35446a2371f62ab20ee12e03c60280cf4
3
+ size 9360384
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6cbd82eb0802df04bde+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05957d9cba27c1402667fc12ea77dc9386ee5d71e470e0906772ef85b8eeacd5
3
+ size 9527051