Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
8c4d961
·
verified ·
1 Parent(s): af8afe4

Synchronizing local compiler cache.

Browse files
Files changed (11) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3/Qwen/Qwen3-0.6B/c783db5745a82fc95b29.json +87 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/compile_flags.json +1 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.done +0 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo +3 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/compile_flags.json +1 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.done +0 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff +3 -0
.gitattributes CHANGED
@@ -5203,3 +5203,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.neff
5203
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5204
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5205
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
5203
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5204
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5205
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5206
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5207
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5208
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3/Qwen/Qwen3-0.6B/c783db5745a82fc95b29.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
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
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "neuron": {
49
+ "_serialized_key": "NxDNeuronConfig",
50
+ "batch_size": 4,
51
+ "capacity_factor": null,
52
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
53
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
54
+ "continuous_batching": true,
55
+ "enable_bucketing": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 4,
60
+ "max_batch_size": 4,
61
+ "max_context_length": 4096,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 4096,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": true,
66
+ "optimum_neuron_version": "0.4.0.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 4096,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn2",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 4
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151936
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51ec4463f406993c156718e436f7065c5b50b96e96b8b29e15b268ac0115b1ea
3
+ size 2446940
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe297ebcf89dd16a03a53e4e0185500341da7cb47d3a219b230b07deae5f353b
3
+ size 2960384
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b49c2c498c3917599c3c0f242acca562739d1f0778cd4d78435f4f5e56ac40
3
+ size 3097299
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99eec1c44bd444e4b8d60de8a8f8657c659b80439364799cae72b731d849a7e
3
+ size 2111671
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca533b51dcc91cd56a104003ab6bc7bc407a36b4afd05e53adb28e120f10cdf1
3
+ size 15719424