Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
596
jburtoft commited on
Commit
24cc14e
·
verified ·
1 Parent(s): 54d800f

Synchronizing local compiler cache.

Browse files
Files changed (31) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/MODULE_7b8e2acf05c9ab9e8fa9+9006d3c6/model.neff +1 -1
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_7b8e2acf05c9ab9e8fa9+9006d3c6/wrapped_neff.hlo +1 -1
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/compile_flags.json +1 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.done +0 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.hlo_module.pb +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.neff +3 -0
  8. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.1/qwen3/Qwen/Qwen3-0.6B/2438be162acfdae5dc19.json +86 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/compile_flags.json +1 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.done +0 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.hlo_module.pb +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.neff +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/compile_flags.json +1 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/model.hlo_module.pb +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/model.hlo_module.pb.lock +0 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/compile_flags.json +1 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/model.hlo_module.pb.lock +0 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/compile_flags.json +1 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.done +0 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.hlo_module.pb +3 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.neff +0 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/compile_flags.json +1 -0
  24. neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.done +0 -0
  25. neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.hlo_module.pb +3 -0
  26. neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.neff +3 -0
  27. neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/compile_flags.json +1 -0
  28. neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.done +0 -0
  29. neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.hlo_module.pb +3 -0
  30. neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.neff +3 -0
  31. neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -12516,3 +12516,7 @@ neuronxcc-2.21.33363.0+82129205/MODULE_b6ab468f70deaeb5f407+a02c3a36/wrapped_nef
12516
  neuronxcc-2.21.33363.0+82129205/MODULE_2b506b28aa70aa427421+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12517
  neuronxcc-2.21.33363.0+82129205/MODULE_2b506b28aa70aa427421+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12518
  neuronxcc-2.21.33363.0+82129205/MODULE_506a007dc635ddb0863f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
12516
  neuronxcc-2.21.33363.0+82129205/MODULE_2b506b28aa70aa427421+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12517
  neuronxcc-2.21.33363.0+82129205/MODULE_2b506b28aa70aa427421+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12518
  neuronxcc-2.21.33363.0+82129205/MODULE_506a007dc635ddb0863f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
12519
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.neff filter=lfs diff=lfs merge=lfs -text
12520
+ neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
12521
+ neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12522
+ neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/MODULE_7b8e2acf05c9ab9e8fa9+9006d3c6/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4600caaa7272258160fec2d98cde259972fdb112fa57deee2fcf3e334492de65
3
  size 2438144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76dbcb548d678c5ed3dff338239911dd3af10e312c6c12e25efb12578c06ccd
3
  size 2438144
neuronxcc-2.21.18209.0+043b1bf7/MODULE_7b8e2acf05c9ab9e8fa9+9006d3c6/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db467f4695b79c85ead16a550d3f0b82ba6060d9feb0f7b64f5731e28cb880f3
3
  size 2685147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a2e304bbc52a7693083cf320cdd204f1e58664d101bc60d75e0e88e3022a97
3
  size 2685147
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ec9aaa37bf9b8671e250c7be8d225a75f04422a2f723d1eeefe7f0719321f3
3
+ size 5432569
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8fd287a13cb7e9f9d890+2667e3c1/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d5b6351750cb3d344f07d8adac4400fccf7a775c326b181d31bf1ff7da11ed
3
+ size 2233344
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.1/qwen3/Qwen/Qwen3-0.6B/2438be162acfdae5dc19.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1,
51
+ "capacity_factor": null,
52
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
53
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
54
+ "continuous_batching": false,
55
+ "ep_degree": 1,
56
+ "fused_qkv": true,
57
+ "glu_mlp": true,
58
+ "local_ranks_size": 2,
59
+ "max_batch_size": 1,
60
+ "max_context_length": 2048,
61
+ "max_topk": 256,
62
+ "n_active_tokens": 2048,
63
+ "neuronxcc_version": "2.21.33363.0+82129205",
64
+ "on_device_sampling": true,
65
+ "optimum_neuron_version": "0.4.1",
66
+ "output_logits": false,
67
+ "pp_degree": 1,
68
+ "sequence_length": 2048,
69
+ "speculation_length": 0,
70
+ "start_rank_id": 0,
71
+ "target": "trn1",
72
+ "torch_dtype": "bfloat16",
73
+ "tp_degree": 2
74
+ },
75
+ "num_attention_heads": 16,
76
+ "num_hidden_layers": 28,
77
+ "num_key_value_heads": 8,
78
+ "rms_norm_eps": 1e-06,
79
+ "rope_scaling": null,
80
+ "rope_theta": 1000000,
81
+ "sliding_window": null,
82
+ "tie_word_embeddings": true,
83
+ "use_cache": true,
84
+ "use_sliding_window": false,
85
+ "vocab_size": 151936
86
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type", "transformer"]
neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3091aeeb1f5e4708c1ad59508c67a1fedd3a516df0e0afac4e15f9bfb2d6f30
3
+ size 344
neuronxcc-2.21.33363.0+82129205/MODULE_11196433285822111861+f7f529f3/model.neff ADDED
Binary file (11.3 kB). View file
 
neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type", "transformer"]
neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a7328ea3d65a8c30f29869238315424beca1b69df859bf2430f37a293c2897
3
+ size 1452418
neuronxcc-2.21.33363.0+82129205/MODULE_17244610172249175385+f7f529f3/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type", "transformer"]
neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4236bcf1ab5012392b997a0b98df79c8e10f445c629acc2c3ed3b20a47f940a
3
+ size 1452900
neuronxcc-2.21.33363.0+82129205/MODULE_3876370926838788815+f7f529f3/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type", "transformer"]
neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd30d5f99355209eb8da231a97ebc540d100b16281997355aa504105badf8fc2
3
+ size 1808
neuronxcc-2.21.33363.0+82129205/MODULE_4216092561315976987+f7f529f3/model.neff ADDED
Binary file (31.7 kB). View file
 
neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+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-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abd2a7b4a3b3a4ef734e16bdb0dff1807b22c136d7aa2a43f79305c57573ad4
3
+ size 671989
neuronxcc-2.21.33363.0+82129205/MODULE_5a09da323fcbfc095411+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb9f3792474cfbe67a6df7866714bd1fb65878a4ef1266180c09ed920dbe658
3
+ size 10916864
neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+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-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2f7b97006fd94793852f160d93db1b377aabab76815ddbb522e9c9f086014d
3
+ size 741435
neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015de9dec63e5e0010f9b2002205ba815709ebdb8152d165d560140cdeea823a
3
+ size 1823744
neuronxcc-2.21.33363.0+82129205/MODULE_5d9e5e622d7dbb4afa6b+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc83d0c03b87e246cfb165f4107be45b941b07a1a71c53772cd58a0c9dc2df94
3
+ size 1961048