Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
optimum-internal-testing-user commited on
Commit
d3897a3
·
verified ·
1 Parent(s): 51ec2ae

Synchronizing local compiler cache.

Browse files
Files changed (15) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/5d91fecb93d8e1d0e384.json +82 -0
  3. neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff +1 -1
  4. neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo +1 -1
  5. neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/compile_flags.json +1 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.done +0 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb +3 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff +1 -1
  10. neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo +1 -1
  11. neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -5854,3 +5854,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/wrapped_nef
5854
  neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5855
  neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5856
  neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
5854
  neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5855
  neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5856
  neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5857
+ neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5858
+ neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5859
+ neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/5d91fecb93d8e1d0e384.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "dtype": "bfloat16",
10
+ "hidden_act": "silu",
11
+ "hidden_size": 896,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4864,
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
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "neuron": {
44
+ "_serialized_key": "NxDNeuronConfig",
45
+ "batch_size": 1,
46
+ "capacity_factor": null,
47
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
48
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
49
+ "continuous_batching": false,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 1,
55
+ "max_context_length": 8192,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 8192,
58
+ "neuronxcc_version": "2.21.33363.0+82129205",
59
+ "on_device_sampling": true,
60
+ "optimum_neuron_version": "0.4.4.dev1",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 8192,
64
+ "speculation_length": 0,
65
+ "start_rank_id": 0,
66
+ "target": "trn1",
67
+ "torch_dtype": "bfloat16",
68
+ "tp_degree": 2
69
+ },
70
+ "num_attention_heads": 14,
71
+ "num_hidden_layers": 24,
72
+ "num_key_value_heads": 2,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "use_cache": true,
79
+ "use_mrope": false,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd1f0f7832922f80018693c7e5f05f2af87da8c5ccd61d46747d7d5dfdf2ddd0
3
  size 1936384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0fff828fd38c1aee43143f27a0465c5581091a6665253c6dd7552af3f6cad4
3
  size 1936384
neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d39862519f89981012eab6c1d75d52c052563ea7b90f1f36150a854435daac50
3
  size 2092575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c576c406877b5b57dd3bbbf4c1f199862c0a000db3a5183fa6daf8e6ec87c6d4
3
  size 2092575
neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+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_30826b478ad3db0c312e+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750f3632ea38b335655fd28f42584cdcaa65b02786976fcd408f8314f9cd17b5
3
+ size 726810
neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c21b8d2c352b0e8f28c965f110de45f1d43dc3e5773994dd2808e2524d999b2
3
+ size 71302144
neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8806f154792b185e952668bf467a6f45313fb98068845916efbb38366b36f80
3
  size 3073024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef93799d48af862b4c7eaf33cd52ec052e50b7f66c1e98a1fbd8a034562a82a
3
  size 3073024
neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9487ed19414eca5f4dfe60bfef8c7487cfa96943f8f65cbbdb3697963cd8a31e
3
  size 3147125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b74f65fb1ccbe1abf57b8c48abb04bc9a50b25249e125bddd26f645ba8b860
3
  size 3147125
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+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_b6a329fd6d4912085786+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c233003f245d49dfb3acc5ee2fc0aa702b00d6a819099020cace88065ec4842
3
+ size 643371
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518ab130bd8f46ee96fbfe9e1ca3aa7ba8bdb781938f46f6ba02a73979d931e4
3
+ size 1721344
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2245dcf5e066ce50a9c705d0a9374948b4f45a57aafe66fde7b227170e89da6a
3
+ size 1877650