Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
695
dacorvo HF Staff commited on
Commit
b20f150
·
verified ·
1 Parent(s): 59d18d2

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/Qwen2.5-7B-Instruct/dfd76d8f5a8b7b1dc3d4.json +85 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/compile_flags.json +1 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.done +0 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.neff +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/compile_flags.json +1 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.done +0 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.neff +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -11470,3 +11470,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f0fb89baf34c70d66e71+a9d440f5/wrapped_nef
11470
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0df1ec79b492f17060e5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11471
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0df1ec79b492f17060e5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11472
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_b898251374a338819882+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
11470
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0df1ec79b492f17060e5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11471
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0df1ec79b492f17060e5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11472
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_b898251374a338819882+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
11473
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
11474
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
11475
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-7B-Instruct/dfd76d8f5a8b7b1dc3d4.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-7B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
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
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "neuron": {
47
+ "_serialized_key": "NxDNeuronConfig",
48
+ "batch_size": 1,
49
+ "capacity_factor": null,
50
+ "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct",
51
+ "checkpoint_revision": "a09a35458c702b33eeacc393d103063234e8bc28",
52
+ "continuous_batching": false,
53
+ "enable_bucketing": false,
54
+ "ep_degree": 1,
55
+ "fused_qkv": false,
56
+ "glu_mlp": true,
57
+ "local_ranks_size": 2,
58
+ "max_batch_size": 1,
59
+ "max_context_length": 4096,
60
+ "max_topk": 256,
61
+ "n_active_tokens": 4096,
62
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
63
+ "on_device_sampling": true,
64
+ "optimum_neuron_version": "0.4.0.dev0",
65
+ "output_logits": false,
66
+ "pp_degree": 1,
67
+ "sequence_length": 4096,
68
+ "speculation_length": 0,
69
+ "start_rank_id": 0,
70
+ "target": "trn1",
71
+ "torch_dtype": "bfloat16",
72
+ "tp_degree": 2
73
+ },
74
+ "num_attention_heads": 28,
75
+ "num_hidden_layers": 28,
76
+ "num_key_value_heads": 4,
77
+ "rms_norm_eps": 1e-06,
78
+ "rope_scaling": null,
79
+ "rope_theta": 1000000.0,
80
+ "sliding_window": null,
81
+ "tie_word_embeddings": false,
82
+ "use_cache": true,
83
+ "use_sliding_window": false,
84
+ "vocab_size": 152064
85
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+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_1224e49774fa43c053d0+ed72d204/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37878a747e1c432935c15011f04f9a433c2992edb8413aeccca7f1cc81e4881f
3
+ size 868004
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1224e49774fa43c053d0+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd05458bec934caa356d342f59db81465d7398735e600a3111b605d6e426f2c
3
+ size 6616064
neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+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_26c0c19200d1d2ddc36b+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6617d53294bafc2207366bceb584e64248f731011a200de43d17cd81ef8166c4
3
+ size 741737
neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c11249f1cb5b1f5b103ee086a660104655974064a73c5acd2e875a065fb96a4
3
+ size 8438784
neuronxcc-2.21.18209.0+043b1bf7/MODULE_26c0c19200d1d2ddc36b+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0599b99e2dc292f958bd3856b024b6a191a1e96b7c0ce9e4c7b9a137de5e78ed
3
+ size 8647693