Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
4d5a7e8
·
verified ·
1 Parent(s): d10e9c2

Synchronizing local compiler cache.

Browse files
Files changed (16) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/01c33dbdb9a7e6fefa00.json +82 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/compile_flags.json +1 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.done +0 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo +3 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/compile_flags.json +1 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.done +0 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff +3 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo +3 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/compile_flags.json +1 -0
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.done +0 -0
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.hlo_module.pb +3 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff +3 -0
.gitattributes CHANGED
@@ -5254,3 +5254,8 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff
5254
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5255
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5256
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
5254
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5255
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5256
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5257
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5258
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5259
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff filter=lfs diff=lfs merge=lfs -text
5260
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5261
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/01c33dbdb9a7e6fefa00.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
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
14
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "batch_size": 1,
45
+ "capacity_factor": null,
46
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
47
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
48
+ "continuous_batching": false,
49
+ "enable_bucketing": false,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 4,
54
+ "max_batch_size": 1,
55
+ "max_context_length": 4096,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 4096,
58
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
59
+ "on_device_sampling": true,
60
+ "optimum_neuron_version": "0.4.1.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 4096,
64
+ "speculation_length": 0,
65
+ "start_rank_id": 0,
66
+ "target": "trn2",
67
+ "torch_dtype": "float32",
68
+ "tp_degree": 4
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-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+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_315517e0acf6029aca9b+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cde91b58c424dbc1ffefec99a1607b8de70254cebab0f5f54daa70b941268bb
3
+ size 1680431
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ec2df95afa4e2a765153eb57f48bb83440d1579103231a2c8e781156820342
3
+ size 1854464
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd3c50e84edf0b15004b6e742e0408c9259a21c1bf012319ae80173f10da31a
3
+ size 2010913
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_4ab2217c-aac3-4953-8de6-d843947f737e/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35
3
+ size 1165
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85d4f3d45bbf9651ceada23cba6ae77d4a907c00d9f0ef79ef8be0434d784e7
3
+ size 123904
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:115d0e758f7e3fb2e73697320baac54b1a8369da68c946247f521193e076d1b9
3
+ size 124800
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+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_f9260d832dabcf299e0e+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d7502da5f9e5ac9b655d42c31d3a2011172032815df62a2c7dbf5cd4e75c88
3
+ size 1878426
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690514bb979276f1dd2bd20877682262fe3f2fc331ef4459c801c17abc72099f
3
+ size 14173184