Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
624

Synchronizing local compiler cache of Maykeye/TinyLLama-v0

#592
by tengomucho HF Staff - opened
base: refs/heads/main
←
from: refs/pr/592
Discussion Files changed
+179
-0
Files changed (21) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/llama/Maykeye/TinyLLama-v0/73cd857f742734a1be3d.json +55 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/qwen2/Qwen/Qwen2.5-1.5B-Instruct/b675b5890f4b6e63dbb8.json +84 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/compile_flags.json +1 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.done +0 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.hlo_module.pb +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.neff +3 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/compile_flags.json +1 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.done +0 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.neff +3 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/wrapped_neff.hlo +3 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/compile_flags.json +1 -0
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.done +0 -0
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.hlo_module.pb +3 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.neff +3 -0
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/wrapped_neff.hlo +3 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/compile_flags.json +1 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.done +0 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.hlo_module.pb +3 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.neff +3 -0
.gitattributes CHANGED
@@ -12510,3 +12510,9 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8623340492324789537+bad9cf09/model.neff f
12510
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_87301aa5994aa3ec3488+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12511
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_87301aa5994aa3ec3488+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12512
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_d520c8be8d8ce950a101+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
12510
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_87301aa5994aa3ec3488+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12511
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_87301aa5994aa3ec3488+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12512
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_d520c8be8d8ce950a101+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
12513
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.neff filter=lfs diff=lfs merge=lfs -text
12514
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.neff filter=lfs diff=lfs merge=lfs -text
12515
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12516
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.neff filter=lfs diff=lfs merge=lfs -text
12517
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12518
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/llama/Maykeye/TinyLLama-v0/73cd857f742734a1be3d.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Maykeye/TinyLLama-v0",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 4,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 64,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 256,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "batch_size": 1,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "Maykeye/TinyLLama-v0",
23
+ "checkpoint_revision": "298338802ab94432b917bcce11382aa151aee50f",
24
+ "continuous_batching": false,
25
+ "ep_degree": 1,
26
+ "fused_qkv": true,
27
+ "glu_mlp": true,
28
+ "local_ranks_size": 4,
29
+ "max_batch_size": 1,
30
+ "max_context_length": 128,
31
+ "max_topk": 256,
32
+ "n_active_tokens": 128,
33
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
34
+ "on_device_sampling": true,
35
+ "optimum_neuron_version": "0.4.1",
36
+ "output_logits": false,
37
+ "pp_degree": 1,
38
+ "sequence_length": 128,
39
+ "speculation_length": 0,
40
+ "start_rank_id": 0,
41
+ "target": "inf2",
42
+ "torch_dtype": "bfloat16",
43
+ "tp_degree": 4
44
+ },
45
+ "num_attention_heads": 16,
46
+ "num_hidden_layers": 8,
47
+ "num_key_value_heads": 16,
48
+ "pretraining_tp": 1,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 10000.0,
52
+ "tie_word_embeddings": false,
53
+ "use_cache": true,
54
+ "vocab_size": 32000
55
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/qwen2/Qwen/Qwen2.5-1.5B-Instruct/b675b5890f4b6e63dbb8.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-1.5B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
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": 21,
45
+ "model_type": "qwen2",
46
+ "neuron": {
47
+ "_serialized_key": "NxDNeuronConfig",
48
+ "batch_size": 1,
49
+ "capacity_factor": null,
50
+ "checkpoint_id": "Qwen/Qwen2.5-1.5B-Instruct",
51
+ "checkpoint_revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306",
52
+ "continuous_batching": false,
53
+ "ep_degree": 1,
54
+ "fused_qkv": false,
55
+ "glu_mlp": true,
56
+ "local_ranks_size": 4,
57
+ "max_batch_size": 1,
58
+ "max_context_length": 128,
59
+ "max_topk": 256,
60
+ "n_active_tokens": 128,
61
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
62
+ "on_device_sampling": true,
63
+ "optimum_neuron_version": "0.4.1",
64
+ "output_logits": false,
65
+ "pp_degree": 1,
66
+ "sequence_length": 128,
67
+ "speculation_length": 0,
68
+ "start_rank_id": 0,
69
+ "target": "inf2",
70
+ "torch_dtype": "bfloat16",
71
+ "tp_degree": 4
72
+ },
73
+ "num_attention_heads": 12,
74
+ "num_hidden_layers": 28,
75
+ "num_key_value_heads": 2,
76
+ "rms_norm_eps": 1e-06,
77
+ "rope_scaling": null,
78
+ "rope_theta": 1000000.0,
79
+ "sliding_window": null,
80
+ "tie_word_embeddings": true,
81
+ "use_cache": true,
82
+ "use_sliding_window": false,
83
+ "vocab_size": 151936
84
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b2dc2b5480bce221c0322fd3abb935ab86229aab8447114046e51223c7fb4d
3
+ size 194123
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b80091d649fccb735ad+cb7c900e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c107036ab44e0183abfa37ba68071ceadb2d78d0ab0391f13fca0846ae0caa4d
3
+ size 236544
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca408abd6e3e7c0268691f26a449ce7eccb2a3ddb05cddbb423ddcc171b6add
3
+ size 204883
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda2e695bdc32436c89f3d0e6ce2c902ddbeb25b12ad78961cd600cf4289acde
3
+ size 277504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba349d50643364f6f6+dfb30fc8/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b44a8c1b8d95d1e84bb17db2620130bf8fbedd2dae1b9314bf6e18190b0440
3
+ size 306640
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9a9aacd329d5fe1820635f5fb154ae6d4a00a6fab89bc6c59fbd8ca4ea2513
3
+ size 731185
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054b257af59636694cf0519a276a16e6b2098433390553bc941f68a5551e451d
3
+ size 1700864
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70bb0ca463f2df78ece6+dfb30fc8/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1521f60013cc67b8fd18dc5a34e48de05bf0bac82bac3615214e85bde1f00f1
3
+ size 1884196
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbee552e5817839b6fc84fc26d0ace9dd86a5a9cceea842df6cb973007e80a1
3
+ size 675365
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a218ba8f3973c5638889+cb7c900e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0c012ec1d4ece83d8abc2cee530aebf6043628d2df93b6992bd89309a5483f
3
+ size 1629184