Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
d394711
·
verified ·
1 Parent(s): fa38ee4

Synchronizing local compiler cache.

Browse files
Files changed (6) hide show
  1. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-0.6B/a65675cac42f945a53ae.json +88 -0
  2. neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.hlo_module.pb +1 -1
  3. neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff +1 -1
  4. neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.hlo_module.pb +1 -1
  5. neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff +1 -1
  6. neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo +1 -1
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-0.6B/a65675cac42f945a53ae.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
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
+ ],
46
+ "max_position_embeddings": 40960,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
54
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 2,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 8192,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 8192,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
65
+ "on_device_sampling": true,
66
+ "optimum_neuron_version": "0.4.4.dev1",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 8192,
70
+ "sequence_parallel_enabled": false,
71
+ "speculation_length": 0,
72
+ "start_rank_id": 0,
73
+ "target": "trn1",
74
+ "torch_dtype": "bfloat16",
75
+ "tp_degree": 2
76
+ },
77
+ "num_attention_heads": 16,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 8,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": null,
82
+ "rope_theta": 1000000,
83
+ "sliding_window": null,
84
+ "tie_word_embeddings": true,
85
+ "use_cache": true,
86
+ "use_sliding_window": false,
87
+ "vocab_size": 151936
88
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fef47c81ea82ae9c1bbccaae8898f0f1394144fe9a54e2da4bc45d116029790
3
  size 843918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261eff5997fc5502abd2934c6d03a16f16a9fe4825e3cdd1d70b7a71dcedc957
3
  size 843918
neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50aaa22c493cf1450cb9f125751cd8cd05e416fe67d116134ce46b5bf9e7ad3
3
  size 96881664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b807a77d244dd1bcd11ba903a78da23985dee79a1183ebf806ebb29b397a8f7
3
  size 96881664
neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:997161170799c3feadc6794401da54098d9f2f51468df12f91269e4905ee2e00
3
  size 758053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f645679ef1301d5034c77ab45d1e900e4bb2587bf70f521d5621b18142d447
3
  size 758053
neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b825fcc27593f1bfcfa9ce79a11da94fdbd8c0c774b6711867cd2d95a6ea017
3
  size 2417664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56b7d13b825ea938e3be42b4a7e04856180bfda6036f5da463bd90eca71edc3
3
  size 2417664
neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24cac0e667d9986fda6b21b502c1560b946f02bf1fd00a0a25726fe168a25d2b
3
  size 2554832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456a7167b59dc42a1c862bacb8406d01a6490f64f9f996ba9e75b08bce5e0ec0
3
  size 2554832