dacorvo HF Staff commited on
Commit
0adc516
·
verified ·
1 Parent(s): 1c50d3f

Synchronizing local compiler cache.

Browse files
.gitattributes CHANGED
@@ -4500,3 +4500,4 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d618b5f6d6f813b7449+ed72d204/model.neff f
4500
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_158c2b755daab1e740a8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4501
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb8c372007f461bd6f30+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4502
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
4500
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_158c2b755daab1e740a8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4501
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb8c372007f461bd6f30+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4502
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4503
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbeafd22a3c0c3e648a5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/smollm3/HuggingFaceTB/SmolLM3-3B/3a9131ad50b2885c33f7.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4,
59
+ "capacity_factor": null,
60
+ "cc_pipeline_tiling_factor": 2,
61
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
62
+ "checkpoint_revision": "1c00fc78bd9cf90108046bc433cb34992480f1c1",
63
+ "continuous_batching": true,
64
+ "enable_bucketing": false,
65
+ "ep_degree": 1,
66
+ "fused_qkv": true,
67
+ "glu_mlp": true,
68
+ "local_ranks_size": 2,
69
+ "logical_nc_config": 1,
70
+ "max_batch_size": 4,
71
+ "max_context_length": 4096,
72
+ "max_topk": 256,
73
+ "n_active_tokens": 4096,
74
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
75
+ "on_device_sampling": true,
76
+ "optimum_neuron_version": "0.3.1.dev5",
77
+ "output_logits": false,
78
+ "pp_degree": 1,
79
+ "sequence_length": 4096,
80
+ "speculation_length": 0,
81
+ "start_rank_id": 0,
82
+ "target": null,
83
+ "torch_dtype": "bfloat16",
84
+ "tp_degree": 2
85
+ },
86
+ "no_rope_layer_interval": 4,
87
+ "no_rope_layers": [
88
+ 1,
89
+ 1,
90
+ 1,
91
+ 0,
92
+ 1,
93
+ 1,
94
+ 1,
95
+ 0,
96
+ 1,
97
+ 1,
98
+ 1,
99
+ 0,
100
+ 1,
101
+ 1,
102
+ 1,
103
+ 0,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 0,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 0,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 0,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 0,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 0
124
+ ],
125
+ "num_attention_heads": 16,
126
+ "num_hidden_layers": 36,
127
+ "num_key_value_heads": 4,
128
+ "pretraining_tp": 2,
129
+ "rms_norm_eps": 1e-06,
130
+ "rope_scaling": null,
131
+ "rope_theta": 5000000.0,
132
+ "sliding_window": null,
133
+ "use_cache": false,
134
+ "use_sliding_window": false,
135
+ "vocab_size": 128256
136
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbeafd22a3c0c3e648a5+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbeafd22a3c0c3e648a5+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbeafd22a3c0c3e648a5+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d5d1ad74b01a2e5e37ac67466bc1dd919fa7ff8a1eb7cc69f4e5b9e0e8041c
3
+ size 827469
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbeafd22a3c0c3e648a5+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84eca67d2edc0ca75360a1494b7fc99f75ffb6a6b8d7347a9bf7f6b43fc63dd8
3
+ size 10978304