Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
669
dacorvo HF Staff commited on
Commit
215af7a
·
verified ·
1 Parent(s): cb3a4fa

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/qwen2/Qwen/Qwen2.5-0.5B/4fc6ac63d94dd444273c.json +82 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/compile_flags.json +1 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.done +0 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.neff +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/wrapped_neff.hlo +3 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/compile_flags.json +1 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.done +0 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -11608,3 +11608,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8368c27a60ca92409518+ed72d204/model.neff
11608
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_69d16930b2b3511b2acb+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11609
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_69d16930b2b3511b2acb+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11610
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a893f8a6887d30576523+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
11608
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_69d16930b2b3511b2acb+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11609
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_69d16930b2b3511b2acb+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11610
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a893f8a6887d30576523+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
11611
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11612
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11613
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/4fc6ac63d94dd444273c.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": 4,
45
+ "capacity_factor": null,
46
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
47
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
48
+ "continuous_batching": true,
49
+ "enable_bucketing": false,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 4,
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": false,
60
+ "optimum_neuron_version": "0.4.0.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 4096,
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-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2920e5fde77a80d2d66c9ba5addf46e53d032f533c7097cba34e31243f84ed
3
+ size 588406
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8e9c3bbcfeb24f5716790979ab5e716ef14dde3f59e799dd36d5e78f3ca4ab
3
+ size 1926144
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04def5b319953baacddd+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d04de06be1013661b7a4bd6bd5b50d9a3dd442f29e23d9767a31edf7170f5d
3
+ size 2082478
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512341341856b75f5a88023d5d6a523af1df1ecccb3f0a6ba5953da3db15a616
3
+ size 739558
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8b706c9cca821e93ed6dc9f8087c3080cdb140bde55128aaddd73941b883f8
3
+ size 26133504