Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF Staff commited on
Commit
c75132d
·
verified ·
1 Parent(s): cd53389

Synchronizing local compiler cache.

Browse files
Files changed (28) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/f0ffd235538c74a62bde.json +55 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/6672e2bf552ce3f0def7.json +49 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/f7c7621fee9c6d43306b.json +49 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/compile_flags.json +1 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.done +0 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.hlo_module.pb +3 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.neff +3 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/compile_flags.json +1 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.done +0 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.hlo_module.pb +3 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.neff +3 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/compile_flags.json +1 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.done +0 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.hlo_module.pb +3 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.neff +3 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/compile_flags.json +1 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.done +0 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.hlo_module.pb +3 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.neff +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/compile_flags.json +1 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.done +0 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.hlo_module.pb +3 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.neff +3 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/compile_flags.json +1 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.done +0 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.hlo_module.pb +3 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -2249,3 +2249,9 @@ neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff fi
2249
  neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2250
  neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2251
  neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
2249
  neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2250
  neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2251
  neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2252
+ neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2253
+ neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2254
+ neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2255
+ neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2256
+ neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
2257
+ neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/f0ffd235538c74a62bde.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "all_reduce_dtype": null,
20
+ "allow_flash_attention": true,
21
+ "attention_layout": "BSH",
22
+ "attn_output_transposed": false,
23
+ "auto_cast_type": "fp32",
24
+ "backend": "hlo",
25
+ "batch_size": 1,
26
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
27
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": false,
30
+ "fuse_qkv": true,
31
+ "group_query_attention": null,
32
+ "log_softmax_scores": false,
33
+ "neuronxcc_version": "2.17.194.0+d312836f",
34
+ "optimum_neuron_version": "0.2.0.dev3",
35
+ "output_all_logits": false,
36
+ "sequence_length": 131072,
37
+ "tp_degree": 2
38
+ },
39
+ "num_attention_heads": 4,
40
+ "num_hidden_layers": 2,
41
+ "num_key_value_heads": 4,
42
+ "pretraining_tp": 1,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_scaling": {
45
+ "factor": 8.0,
46
+ "high_freq_factor": 4.0,
47
+ "low_freq_factor": 1.0,
48
+ "original_max_position_embeddings": 8192,
49
+ "rope_type": "llama3"
50
+ },
51
+ "rope_theta": 500000.0,
52
+ "tie_word_embeddings": false,
53
+ "use_cache": true,
54
+ "vocab_size": 128256
55
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/6672e2bf552ce3f0def7.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "all_reduce_dtype": null,
18
+ "allow_flash_attention": true,
19
+ "attention_layout": "HSB",
20
+ "attn_output_transposed": false,
21
+ "auto_cast_type": "fp32",
22
+ "backend": "hlo",
23
+ "batch_size": 1,
24
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
25
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
26
+ "collectives_layout": "HSB",
27
+ "continuous_batching": false,
28
+ "fuse_qkv": false,
29
+ "group_query_attention": "shard-over-heads",
30
+ "log_softmax_scores": false,
31
+ "neuronxcc_version": "2.17.194.0+d312836f",
32
+ "optimum_neuron_version": "0.2.0.dev3",
33
+ "output_all_logits": false,
34
+ "sequence_length": 128,
35
+ "tp_degree": 2
36
+ },
37
+ "num_attention_heads": 14,
38
+ "num_hidden_layers": 24,
39
+ "num_key_value_heads": 2,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": null,
42
+ "rope_theta": 1000000.0,
43
+ "sliding_window": 32768,
44
+ "tie_word_embeddings": true,
45
+ "use_cache": true,
46
+ "use_mrope": false,
47
+ "use_sliding_window": false,
48
+ "vocab_size": 151936
49
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/f7c7621fee9c6d43306b.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "all_reduce_dtype": null,
18
+ "allow_flash_attention": true,
19
+ "attention_layout": "HSB",
20
+ "attn_output_transposed": false,
21
+ "auto_cast_type": "fp32",
22
+ "backend": "hlo",
23
+ "batch_size": 1,
24
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
25
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
26
+ "collectives_layout": "HSB",
27
+ "continuous_batching": false,
28
+ "fuse_qkv": false,
29
+ "group_query_attention": "replicated-heads",
30
+ "log_softmax_scores": false,
31
+ "neuronxcc_version": "2.17.194.0+d312836f",
32
+ "optimum_neuron_version": "0.2.0.dev3",
33
+ "output_all_logits": false,
34
+ "sequence_length": 128,
35
+ "tp_degree": 24
36
+ },
37
+ "num_attention_heads": 14,
38
+ "num_hidden_layers": 24,
39
+ "num_key_value_heads": 2,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": null,
42
+ "rope_theta": 1000000.0,
43
+ "sliding_window": 32768,
44
+ "tie_word_embeddings": true,
45
+ "use_cache": true,
46
+ "use_mrope": false,
47
+ "use_sliding_window": false,
48
+ "vocab_size": 151936
49
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f2ade06e6bd7f532c121ba34190998ff35dd497f016a58850b862ba532e025
3
+ size 253034
neuronxcc-2.17.194.0+d312836f/MODULE_2ae37ee2c7255cce8028+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddabcb22476d81434e498f1060954e0c3ece3e4ab09ed47630f8380b64bc363f
3
+ size 482304
neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10522391bb6a18d7514c5e4bbd5263485db968acc7d1919b77f31ce89d5b9bdb
3
+ size 211801
neuronxcc-2.17.194.0+d312836f/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da380680317d0aa45cbcdbb17fb24482a543d595b179651260206ff80f9e0465
3
+ size 502784
neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bbc25d2825e7c7f0b6598c9c83f441b70cbe384b1b927cc6aa410b26925f7b
3
+ size 19946
neuronxcc-2.17.194.0+d312836f/MODULE_892a0bb27ce39228be75+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe401d706e2386a430ba6d53ea7004af0827d67d4b58a02019d54f026e95557c
3
+ size 513024
neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54e05c7da5f67a57c2d071b1671e6aff32781cd77a7af06b80c2a818974e9f5
3
+ size 270397
neuronxcc-2.17.194.0+d312836f/MODULE_c24af7fcf05443daf3b7+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c430dd7797bd2f5a1e7c87dcbf9a0b5d4162ac96886c1265c78a36bcc9422241
3
+ size 1035264
neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70343b242fbdae67bbf4f00cc5bb455edad6fa5873e803a322633ad7d05bf08
3
+ size 27085
neuronxcc-2.17.194.0+d312836f/MODULE_e3aea5d1517d9896fd33+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a71b5909de7d26af2d6391211132c59a9b4938329f971b6f54be77fb734d18
3
+ size 221174784
neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3aca8b70db402527f76fbcfb65417f7d367783b2c59d70b9adfa75fc5825002
3
+ size 220090
neuronxcc-2.17.194.0+d312836f/MODULE_fd6170cedb4fe53c8433+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be44e2d915dd8e260469e5d4a0bed94f49ee8c5e729d227b5859e6c83d412f4
3
+ size 1178624