Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
c1cafb3
·
verified ·
1 Parent(s): d6b5bb5

Synchronizing local compiler cache.

Browse files
Files changed (20) hide show
  1. .gitattributes +1 -0
  2. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/7d1306ff15a027b78674.json +77 -0
  3. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/4fc129d62e717e99d4bc.json +71 -0
  4. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/696fa08b912df4a8f708.json +71 -0
  5. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.hlo_module.pb +1 -1
  6. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.neff +1 -1
  7. neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/compile_flags.json +1 -0
  8. neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.done +0 -0
  9. neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.hlo_module.pb +3 -0
  10. neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.neff +3 -0
  11. neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff +0 -0
  12. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.neff +1 -1
  13. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/wrapped_neff.hlo +1 -1
  14. neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/model.neff +1 -1
  15. neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/wrapped_neff.hlo +1 -1
  16. neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.hlo_module.pb +1 -1
  17. neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.neff +1 -1
  18. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.neff +1 -1
  19. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/wrapped_neff.hlo +1 -1
  20. neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff +1 -1
.gitattributes CHANGED
@@ -3252,3 +3252,4 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_ef8771b8447d48519ae4+431f5505/model.neff fi
3252
  neuronxcc-2.18.121.0+9e31e41a/MODULE_1bce819dd943e86ebacb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3253
  neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3254
  neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
3252
  neuronxcc-2.18.121.0+9e31e41a/MODULE_1bce819dd943e86ebacb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3253
  neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3254
  neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3255
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/7d1306ff15a027b78674.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "llamafactory/tiny-random-Llama-3",
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": 16,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 64,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "async_mode": false,
21
+ "attn_kernel_enabled": false,
22
+ "batch_size": 1,
23
+ "capacity_factor": null,
24
+ "cc_pipeline_tiling_factor": 2,
25
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
26
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
27
+ "continuous_batching": false,
28
+ "enable_bucketing": false,
29
+ "ep_degree": 1,
30
+ "flash_decoding_enabled": false,
31
+ "fused_qkv": true,
32
+ "glu_mlp": true,
33
+ "is_chunked_prefill": false,
34
+ "local_ranks_size": 2,
35
+ "logical_nc_config": 1,
36
+ "max_batch_size": 1,
37
+ "max_context_length": 131072,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 131072,
42
+ "neuronxcc_version": "2.18.121.0+9e31e41a",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev2",
46
+ "output_logits": false,
47
+ "padding_side": "right",
48
+ "pp_degree": 1,
49
+ "qk_layernorm": false,
50
+ "qkv_kernel_enabled": false,
51
+ "rpl_reduce_dtype": "bfloat16",
52
+ "sequence_length": 131072,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "bfloat16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 4,
62
+ "num_hidden_layers": 2,
63
+ "num_key_value_heads": 4,
64
+ "pretraining_tp": 1,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": {
67
+ "factor": 8.0,
68
+ "high_freq_factor": 4.0,
69
+ "low_freq_factor": 1.0,
70
+ "original_max_position_embeddings": 8192,
71
+ "rope_type": "llama3"
72
+ },
73
+ "rope_theta": 500000.0,
74
+ "tie_word_embeddings": false,
75
+ "use_cache": true,
76
+ "vocab_size": 128256
77
+ }
neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/4fc129d62e717e99d4bc.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 1,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
24
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
25
+ "continuous_batching": false,
26
+ "enable_bucketing": false,
27
+ "ep_degree": 1,
28
+ "flash_decoding_enabled": false,
29
+ "fused_qkv": false,
30
+ "glu_mlp": true,
31
+ "is_chunked_prefill": false,
32
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 1,
35
+ "max_context_length": 4096,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 4096,
40
+ "neuronxcc_version": "2.18.121.0+9e31e41a",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev2",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 4096,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 14,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 32768,
66
+ "tie_word_embeddings": true,
67
+ "use_cache": true,
68
+ "use_mrope": false,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/696fa08b912df4a8f708.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 1,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
24
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
25
+ "continuous_batching": false,
26
+ "enable_bucketing": false,
27
+ "ep_degree": 1,
28
+ "flash_decoding_enabled": false,
29
+ "fused_qkv": false,
30
+ "glu_mlp": true,
31
+ "is_chunked_prefill": false,
32
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 1,
35
+ "max_context_length": 128,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 128,
40
+ "neuronxcc_version": "2.18.121.0+9e31e41a",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev2",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 128,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 14,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 32768,
66
+ "tie_word_embeddings": true,
67
+ "use_cache": true,
68
+ "use_mrope": false,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ad438ab09ba805e35aa5c056da9aaa135edda0fe87ed3d1597ef8922be31734
3
  size 689263
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f944f33e56297c279c172dfaa19060a67187aed50c81c377792dcbb4c9eba73a
3
  size 689263
neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dea93f6c8948d51a4155fd96d89cfa28f3c85f7c2d30f901e913a990cda64a69
3
  size 19590144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6d2ca28cc01af7109c4c65510298705bf7744bb1786aeb8f46ec521e2cc120
3
  size 19590144
neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5385a23cc48b16937018f0542a2b5261662d2aff64f914a606bbea1e0bdd4f48
3
+ size 567194
neuronxcc-2.18.121.0+9e31e41a/MODULE_17de2205f692a10a3037+84f3e719/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbadcbd341e833eb64794383b722b1818871c6cc4c59ee8aa81476163ddaa22
3
+ size 1158144
neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff differ
 
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d5b9058e56432b0ecee8eec52dd0d28d5607a677ed2e91c3d0b801a56cded8
3
  size 1086464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e9e90c71709ff10e7debb06b315dbc61967b93336950c5569d171100d3ec7f
3
  size 1086464
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:985424155329c6aa31e3db81b9725f036821c1c34e1da827a85fc5b3f7aaceaf
3
  size 1231490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca4af719e6a8212aa7fa2ddeb02c4c38a5285fff0b84b185a2b2f6bc7bc9a31
3
  size 1231490
neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9acc3248dd65217ef8f99e699cf599f1042276f0242dc329c2415b0916484a7d
3
  size 461824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b622ecda9db18cc072854a19311b3131f52be56529d3d481dcfb9e7758788bad
3
  size 461824
neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c039410374dcf762bad0a8a1ca460bd7428a3a5d3e707f13467b2c2b5d270cbc
3
  size 469663
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65daab6965acbe72bb8c3c33652c59a1a8bb5f6782878593161906110e2190a3
3
  size 469663
neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680e74012140d8f46546d07484b03b3922fe76d2140f36d71daa840ce664bea2
3
  size 91602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5942df416d422ff6863714bb5916f15da676e4783afe8e88398a554eda27d2c
3
  size 91602
neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33950f21a662e3dfab5c3079eb6a0e14244c9dd6afcecb017e4d7ad66380222a
3
  size 213474304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3ee655d34e16d614da02c125d6a6aed146ff0bed90475ff1d61445a58d1591
3
  size 213474304
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c289c15830e8e1e8436a7499be61ed9a4d85c0726134623054ca66a0673dcbd
3
  size 1178624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4148941c3f23affc8917c1c05e5589288bb86660b6698feb3c016304a815d3a2
3
  size 1178624
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceaed7382d02fc957d2ea251ec2fc675cad0bc5bc722793ff63e131181cf8f0a
3
  size 1323650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e47e9b44c4a214525c87db7e7deb34ecdcdf487cdcd7c263e4b455fcda4ad0
3
  size 1323650
neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2267ef602a5b10390fc2b2eb6e20f49c9fa3557264c952b76280c844f1de23d7
3
  size 594944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85927fea8fe635bba24f2493467926e77a7140c4ccfde97b7e622e6757278190
3
  size 594944