Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
3e16e6d
·
verified ·
1 Parent(s): 2807094

Synchronizing local compiler cache.

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4c5b9cb78dab4bbd871f.json +51 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8456948f6fde59831390.json +51 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8c9f1fab702cddae6156.json +51 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/1fb5c6b213ce9eb31109.json +55 -0
  5. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/be6cf655a8b36069d883.json +55 -0
  6. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/bf840674318c6cdc6330.json +77 -0
  7. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/c59993fff4b07fbeb262.json +77 -0
  8. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/e4975f3e0d271e6155e4.json +55 -0
  9. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/fb64b85b484e3ebb9a1d.json +77 -0
  10. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/unsloth/Llama-3.2-1B-Instruct/14f6b812ab3b13c199f1.json +56 -0
  11. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/1c3abae211f3e919b7f0.json +73 -0
  12. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/b21b3ac2511d590ac1c2.json +73 -0
  13. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/baf0fb4d07ac05e74df7.json +73 -0
  14. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/076d544cf144121b2024.json +52 -0
  15. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/9da282b561774776761c.json +52 -0
  16. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/bcf8d0c54c45b277333b.json +52 -0
  17. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/0dd437c3697ceec3b894.json +53 -0
  18. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/44c8abc3ecedc8598f8a.json +53 -0
  19. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/d472f81e5c657f79c2f9.json +53 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff +1 -1
  21. neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff +1 -1
  22. neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff +1 -1
  23. neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff +1 -1
  24. neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +1 -1
  25. neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +1 -1
  26. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb +1 -1
  27. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff +1 -1
  28. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo +1 -1
  29. neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff +1 -1
  30. neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +1 -1
  31. neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff +1 -1
  32. neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff +1 -1
  33. neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff +1 -1
  34. neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +1 -1
  35. neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff +1 -1
  36. neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff +1 -1
  37. neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff +1 -1
  38. neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff +1 -1
  39. neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff +1 -1
  40. neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +1 -1
  41. neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +1 -1
  42. neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff +1 -1
  43. neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff +1 -1
  44. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb +1 -1
  45. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff +1 -1
  46. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo +1 -1
  47. neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff +1 -1
  48. neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff +1 -1
  49. neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff +1 -1
  50. neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.hlo_module.pb +1 -1
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4c5b9cb78dab4bbd871f.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "GraniteForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attention_multiplier": 1.0,
11
+ "embedding_multiplier": 1.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 64,
16
+ "logits_scaling": 1.0,
17
+ "max_position_embeddings": 2048,
18
+ "mlp_bias": false,
19
+ "model_type": "granite",
20
+ "neuron": {
21
+ "_serialized_key": "HloNeuronConfig",
22
+ "all_reduce_dtype": null,
23
+ "allow_flash_attention": true,
24
+ "attention_layout": "HSB",
25
+ "attn_output_transposed": false,
26
+ "auto_cast_type": "fp16",
27
+ "batch_size": 1,
28
+ "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
29
+ "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
30
+ "collectives_layout": "HSB",
31
+ "continuous_batching": false,
32
+ "fuse_qkv": true,
33
+ "group_query_attention": null,
34
+ "log_softmax_scores": false,
35
+ "neuronxcc_version": "2.17.194.0+d312836f",
36
+ "optimum_neuron_version": "0.2.0.dev6",
37
+ "output_all_logits": false,
38
+ "sequence_length": 100,
39
+ "tp_degree": 2
40
+ },
41
+ "num_attention_heads": 4,
42
+ "num_hidden_layers": 2,
43
+ "num_key_value_heads": 4,
44
+ "residual_multiplier": 1.0,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 10000.0,
48
+ "tie_word_embeddings": false,
49
+ "use_cache": true,
50
+ "vocab_size": 49152
51
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8456948f6fde59831390.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "GraniteForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attention_multiplier": 1.0,
11
+ "embedding_multiplier": 1.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 64,
16
+ "logits_scaling": 1.0,
17
+ "max_position_embeddings": 2048,
18
+ "mlp_bias": false,
19
+ "model_type": "granite",
20
+ "neuron": {
21
+ "_serialized_key": "HloNeuronConfig",
22
+ "all_reduce_dtype": null,
23
+ "allow_flash_attention": true,
24
+ "attention_layout": "HSB",
25
+ "attn_output_transposed": false,
26
+ "auto_cast_type": "fp16",
27
+ "batch_size": 2,
28
+ "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
29
+ "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
30
+ "collectives_layout": "HSB",
31
+ "continuous_batching": true,
32
+ "fuse_qkv": true,
33
+ "group_query_attention": null,
34
+ "log_softmax_scores": false,
35
+ "neuronxcc_version": "2.17.194.0+d312836f",
36
+ "optimum_neuron_version": "0.2.0.dev6",
37
+ "output_all_logits": false,
38
+ "sequence_length": 100,
39
+ "tp_degree": 2
40
+ },
41
+ "num_attention_heads": 4,
42
+ "num_hidden_layers": 2,
43
+ "num_key_value_heads": 4,
44
+ "residual_multiplier": 1.0,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 10000.0,
48
+ "tie_word_embeddings": false,
49
+ "use_cache": true,
50
+ "vocab_size": 49152
51
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8c9f1fab702cddae6156.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "GraniteForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attention_multiplier": 1.0,
11
+ "embedding_multiplier": 1.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 64,
16
+ "logits_scaling": 1.0,
17
+ "max_position_embeddings": 2048,
18
+ "mlp_bias": false,
19
+ "model_type": "granite",
20
+ "neuron": {
21
+ "_serialized_key": "HloNeuronConfig",
22
+ "all_reduce_dtype": null,
23
+ "allow_flash_attention": true,
24
+ "attention_layout": "HSB",
25
+ "attn_output_transposed": false,
26
+ "auto_cast_type": "bf16",
27
+ "batch_size": 1,
28
+ "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
29
+ "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
30
+ "collectives_layout": "HSB",
31
+ "continuous_batching": false,
32
+ "fuse_qkv": true,
33
+ "group_query_attention": null,
34
+ "log_softmax_scores": false,
35
+ "neuronxcc_version": "2.17.194.0+d312836f",
36
+ "optimum_neuron_version": "0.2.0.dev6",
37
+ "output_all_logits": false,
38
+ "sequence_length": 100,
39
+ "tp_degree": 2
40
+ },
41
+ "num_attention_heads": 4,
42
+ "num_hidden_layers": 2,
43
+ "num_key_value_heads": 4,
44
+ "residual_multiplier": 1.0,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 10000.0,
48
+ "tie_word_embeddings": false,
49
+ "use_cache": true,
50
+ "vocab_size": 49152
51
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/1fb5c6b213ce9eb31109.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
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": true,
22
+ "attention_layout": "BSH",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "bf16",
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.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
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.dev6/llama/llamafactory/tiny-random-Llama-3/be6cf655a8b36069d883.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
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": true,
22
+ "attention_layout": "BSH",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "fp16",
25
+ "batch_size": 2,
26
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
27
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": true,
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.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
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.dev6/llama/llamafactory/tiny-random-Llama-3/bf840674318c6cdc6330.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": 100,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 100,
42
+ "neuronxcc_version": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.2.0.dev6",
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": "float16",
52
+ "sequence_length": 100,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "float16",
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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/c59993fff4b07fbeb262.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": 100,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 100,
42
+ "neuronxcc_version": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.2.0.dev6",
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": 100,
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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/llamafactory/tiny-random-Llama-3/e4975f3e0d271e6155e4.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
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": true,
22
+ "attention_layout": "BSH",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "fp16",
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.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
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.dev6/llama/llamafactory/tiny-random-Llama-3/fb64b85b484e3ebb9a1d.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": 2,
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": true,
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": 2,
37
+ "max_context_length": 100,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 100,
42
+ "neuronxcc_version": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": false,
45
+ "optimum_neuron_version": "0.2.0.dev6",
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": "float16",
52
+ "sequence_length": 100,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "float16",
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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/llama/unsloth/Llama-3.2-1B-Instruct/14f6b812ab3b13c199f1.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Llama-3.2-1B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": true,
22
+ "attention_layout": "BSH",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "fp16",
25
+ "batch_size": 4,
26
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
27
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": true,
30
+ "fuse_qkv": true,
31
+ "group_query_attention": "shard-over-heads",
32
+ "log_softmax_scores": false,
33
+ "neuronxcc_version": "2.17.194.0+d312836f",
34
+ "optimum_neuron_version": "0.2.0.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 4096,
37
+ "tp_degree": 2
38
+ },
39
+ "num_attention_heads": 32,
40
+ "num_hidden_layers": 16,
41
+ "num_key_value_heads": 8,
42
+ "pretraining_tp": 1,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_scaling": {
45
+ "factor": 32.0,
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": true,
53
+ "unsloth_fixed": true,
54
+ "use_cache": true,
55
+ "vocab_size": 128256
56
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/1c3abae211f3e919b7f0.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
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": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
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": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.2.0.dev6",
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": "float16",
50
+ "sequence_length": 100,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "float16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 32,
60
+ "num_experts_per_tok": 2,
61
+ "num_hidden_layers": 2,
62
+ "num_key_value_heads": 8,
63
+ "num_local_experts": 8,
64
+ "output_router_logits": false,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_theta": 10000.0,
67
+ "router_aux_loss_coef": 0.001,
68
+ "router_jitter_noise": 0.0,
69
+ "sliding_window": 4096,
70
+ "tie_word_embeddings": false,
71
+ "use_cache": true,
72
+ "vocab_size": 32000
73
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/b21b3ac2511d590ac1c2.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
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": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
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": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.2.0.dev6",
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": 100,
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": 32,
60
+ "num_experts_per_tok": 2,
61
+ "num_hidden_layers": 2,
62
+ "num_key_value_heads": 8,
63
+ "num_local_experts": 8,
64
+ "output_router_logits": false,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_theta": 10000.0,
67
+ "router_aux_loss_coef": 0.001,
68
+ "router_jitter_noise": 0.0,
69
+ "sliding_window": 4096,
70
+ "tie_word_embeddings": false,
71
+ "use_cache": true,
72
+ "vocab_size": 32000
73
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/mixtral/dacorvo/Mixtral-tiny/baf0fb4d07ac05e74df7.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 2,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
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": 2,
35
+ "max_context_length": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.2.0.dev6",
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": "float16",
50
+ "sequence_length": 100,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "float16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 32,
60
+ "num_experts_per_tok": 2,
61
+ "num_hidden_layers": 2,
62
+ "num_key_value_heads": 8,
63
+ "num_local_experts": 8,
64
+ "output_router_logits": false,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_theta": 10000.0,
67
+ "router_aux_loss_coef": 0.001,
68
+ "router_jitter_noise": 0.0,
69
+ "sliding_window": 4096,
70
+ "tie_word_embeddings": false,
71
+ "use_cache": true,
72
+ "vocab_size": 32000
73
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/076d544cf144121b2024.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/phi-4-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Phi3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {},
11
+ "embd_pdrop": 0.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 32,
16
+ "max_position_embeddings": 16384,
17
+ "model_type": "phi3",
18
+ "neuron": {
19
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": false,
22
+ "attention_layout": "HSB",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "fp16",
25
+ "batch_size": 2,
26
+ "checkpoint_id": "yujiepan/phi-4-tiny-random",
27
+ "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": true,
30
+ "fuse_qkv": true,
31
+ "group_query_attention": "replicated-heads",
32
+ "log_softmax_scores": false,
33
+ "neuronxcc_version": "2.17.194.0+d312836f",
34
+ "optimum_neuron_version": "0.2.0.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
37
+ "tp_degree": 2
38
+ },
39
+ "num_attention_heads": 2,
40
+ "num_hidden_layers": 2,
41
+ "num_key_value_heads": 1,
42
+ "original_max_position_embeddings": 16384,
43
+ "partial_rotary_factor": 1.0,
44
+ "resid_pdrop": 0.0,
45
+ "rms_norm_eps": 1e-05,
46
+ "rope_scaling": null,
47
+ "rope_theta": 250000,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "vocab_size": 100352
52
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/9da282b561774776761c.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/phi-4-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Phi3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {},
11
+ "embd_pdrop": 0.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 32,
16
+ "max_position_embeddings": 16384,
17
+ "model_type": "phi3",
18
+ "neuron": {
19
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": false,
22
+ "attention_layout": "HSB",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "fp16",
25
+ "batch_size": 1,
26
+ "checkpoint_id": "yujiepan/phi-4-tiny-random",
27
+ "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": false,
30
+ "fuse_qkv": true,
31
+ "group_query_attention": "replicated-heads",
32
+ "log_softmax_scores": false,
33
+ "neuronxcc_version": "2.17.194.0+d312836f",
34
+ "optimum_neuron_version": "0.2.0.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
37
+ "tp_degree": 2
38
+ },
39
+ "num_attention_heads": 2,
40
+ "num_hidden_layers": 2,
41
+ "num_key_value_heads": 1,
42
+ "original_max_position_embeddings": 16384,
43
+ "partial_rotary_factor": 1.0,
44
+ "resid_pdrop": 0.0,
45
+ "rms_norm_eps": 1e-05,
46
+ "rope_scaling": null,
47
+ "rope_theta": 250000,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "vocab_size": 100352
52
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/phi3/yujiepan/phi-4-tiny-random/bcf8d0c54c45b277333b.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/phi-4-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Phi3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {},
11
+ "embd_pdrop": 0.0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 32,
16
+ "max_position_embeddings": 16384,
17
+ "model_type": "phi3",
18
+ "neuron": {
19
+ "_serialized_key": "HloNeuronConfig",
20
+ "all_reduce_dtype": null,
21
+ "allow_flash_attention": false,
22
+ "attention_layout": "HSB",
23
+ "attn_output_transposed": false,
24
+ "auto_cast_type": "bf16",
25
+ "batch_size": 1,
26
+ "checkpoint_id": "yujiepan/phi-4-tiny-random",
27
+ "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
28
+ "collectives_layout": "HSB",
29
+ "continuous_batching": false,
30
+ "fuse_qkv": true,
31
+ "group_query_attention": "replicated-heads",
32
+ "log_softmax_scores": false,
33
+ "neuronxcc_version": "2.17.194.0+d312836f",
34
+ "optimum_neuron_version": "0.2.0.dev6",
35
+ "output_all_logits": false,
36
+ "sequence_length": 100,
37
+ "tp_degree": 2
38
+ },
39
+ "num_attention_heads": 2,
40
+ "num_hidden_layers": 2,
41
+ "num_key_value_heads": 1,
42
+ "original_max_position_embeddings": 16384,
43
+ "partial_rotary_factor": 1.0,
44
+ "resid_pdrop": 0.0,
45
+ "rms_norm_eps": 1e-05,
46
+ "rope_scaling": null,
47
+ "rope_theta": 250000,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "vocab_size": 100352
52
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/0dd437c3697ceec3b894.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "HloNeuronConfig",
18
+ "all_reduce_dtype": null,
19
+ "allow_flash_attention": true,
20
+ "attention_layout": "HSB",
21
+ "attn_output_transposed": false,
22
+ "auto_cast_type": "fp16",
23
+ "batch_size": 1,
24
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
25
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
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.dev6",
33
+ "output_all_logits": false,
34
+ "sequence_length": 100,
35
+ "tp_degree": 2
36
+ },
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 2,
39
+ "num_key_value_heads": 2,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "factor": 4.0,
43
+ "original_max_position_embeddings": 32768,
44
+ "rope_type": "yarn",
45
+ "type": "yarn"
46
+ },
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": 131072,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 152064
53
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/44c8abc3ecedc8598f8a.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "HloNeuronConfig",
18
+ "all_reduce_dtype": null,
19
+ "allow_flash_attention": true,
20
+ "attention_layout": "HSB",
21
+ "attn_output_transposed": false,
22
+ "auto_cast_type": "bf16",
23
+ "batch_size": 1,
24
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
25
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
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.dev6",
33
+ "output_all_logits": false,
34
+ "sequence_length": 100,
35
+ "tp_degree": 2
36
+ },
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 2,
39
+ "num_key_value_heads": 2,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "factor": 4.0,
43
+ "original_max_position_embeddings": 32768,
44
+ "rope_type": "yarn",
45
+ "type": "yarn"
46
+ },
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": 131072,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 152064
53
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/d472f81e5c657f79c2f9.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "HloNeuronConfig",
18
+ "all_reduce_dtype": null,
19
+ "allow_flash_attention": true,
20
+ "attention_layout": "HSB",
21
+ "attn_output_transposed": false,
22
+ "auto_cast_type": "fp16",
23
+ "batch_size": 2,
24
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
25
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
26
+ "collectives_layout": "HSB",
27
+ "continuous_batching": true,
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.dev6",
33
+ "output_all_logits": false,
34
+ "sequence_length": 100,
35
+ "tp_degree": 2
36
+ },
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 2,
39
+ "num_key_value_heads": 2,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "factor": 4.0,
43
+ "original_max_position_embeddings": 32768,
44
+ "rope_type": "yarn",
45
+ "type": "yarn"
46
+ },
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": 131072,
49
+ "tie_word_embeddings": false,
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 152064
53
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:104f51ab3675a23b89a21db5993a27e9a5eeb09867470734c4497617e146159f
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9087c314f6fa55423fc6a68ce21fe41a23755e3187e5ca7b6262bb32852394b8
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f539c4d46bd7143bb99ab78bed121b4565d8bbb9b15cd5fb0d86fa42eabeac7
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718f1087fa929f9e8019a422802ca71044b98f0f2737a1946a86fad0e34be7c4
3
  size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4017e0a785242f34f89ad69149e5db39b1a813f6c647b8b31659cc1f0868e99
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433777267e8f7fbdf53f2c5d8ea049016dc5ac3db4ce58c1013158cac1b7fec9
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfd560af6819825c7e6f05303464c481e10d74ad257fc87de57528001c694afe
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e3d7eba41dec4525d00434677bda5b3628a20542f8dac4da11a04905ec8603
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d20351b22fb897e1f04a4638ab32aea1487833c6b89eca18339835ba2fe27093
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2998d347ffb4da8ad8ae85b0de34b3708c9b95ab1a3d3a6ef3724d39101214db
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c20e3490f8986d6c6745d61708f73050a5ed63c89abe7876449170ae3914ddc
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8658d7edca7655f8ccb268fe74d58fb5c0e28ce000767e740e040effb86a324
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc90fd439316fffc61e3d8c3621617633a5cb8d08dda6c0736121c32054c76bf
3
  size 68277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae03fcab3b8d64ae3d2021aa19538fd99e346fbcb83856c5605c4708c68a674
3
  size 68277
neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b88ebb6d4762cb58b080eb10990ffb1777c6b5dc0aec53275fbe9a973c9fe294
3
  size 257024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59365c55ac85b4319e6652d308793be3f7770506d36d9a898c3c95994f19ad97
3
  size 257024
neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dce1d8a73f724c37e0b050e6aabdd2a403608d397273e8ab815bd28129ade55
3
  size 268322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbb2da6842ffd61c068a7dad0614707927a24cdeb69847ace43b44d48701cd8
3
  size 268322
neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8a1c8c7baf1dd72136b79095ec0210f7f7ea3d2a0aec460b4b0d187d2c2d03d
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a436f46163b80d40e3bcdf3710bae3f53053542d3a20179699b69e649a66f94
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55d6ee114007d520d9c57754d8e1ea3a59eec00c4e6fa2f8168ded13fe644d38
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef98b073c4b799ee1cebf406f19161d2bff5d27ebf91a7780cbc3309bb443372
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba2fd19607592f515c10a8c9aa2bc7fe0a7cfdb61286057096848075d43a85f1
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bdd6ea59a8bd73ff49bdb300a19c9c89e924f848b46f58fc0350c770d9a1aeb
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b956eaad5b3ff2e9453f6a41327cb43195efebec1d36ee916427be098eee31f6
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef05748f5996defa4be3ceb641b0afd5d573c02a707427f39dc316f28b1da5b
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:287a3588ce8935f52349c24164e47aa539bd56ee6df2ab77d46e95b3ee22d9c2
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6c2a97e73faa481af38694827d8c5cc6ba040780fe793cd59333e5d2fa99f6
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0b07361864dbb9075ea5b55536a3b994ae2afd864ff5545d540a4abcf2cafc
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1a2489ae30050340d2a2d74b2f99e125ce55e7af649559b69436f1bbc1254a
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3149c0dbff0f466cd18a167e6e043d018273baf5052a70b152409896e9bdfb3
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcf15abaffa10d5ccb148094aea3c11796dd108eef543d2c169791b865bc239
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e888aa43d68dd17d8a2e6425673085c9bf287b06dfb07cbdd37af13015759b3
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e905bcf110b6673f11faf97fb29fce488607c5de39d5ec35dd07d086353d8a78
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca0de0953ce248253fdedd0742bb581867a5c190e69d0ae38290643a44dedb6c
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f93c2ed8e16a660030c2962766e8574b694a4d3d1a5d715db9f68b047830da2
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92e21aa5950e02ef4f5cb0bb15b2c72bb3ab52cb2b08df8ceea51caac12ed808
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf30589edfe8ba7f48c911fbf185782d5d19b48913922c257b3dd6ffde9fd18
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36efce145688562b0282e7ef51a43f3dce3f4f7374733bd83ead4d3f8db13931
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba211abd63e7ed62b5d57d0a4d73db93c7a282e59a7f9fdabcb6efed59c099f
3
  size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eb60cb7e749593797f7592d265d0f9624eccf916ae74c891d6f86c71845ce55
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e3d53dcf1b9f2fcb975c725d8fb256a6a3319118511e15ac3ba34e410a6956
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5d5d72f55cede7d9f840e9d12ee6d31b8a1091ea81c53727fc6b1824a8f49d2
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969bf0657f95b712f172b4bd0e69d6ded550c83713c18ca22e8d2e9194c74ea4
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d8a29e71654f0529198c27232daa1cddfd5dea5c29d249af21df6a0e3c61331
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a84ebe3c800ade3de31e6eaf3688059f5b5fdd90e09214dbc0cf2872305adf0
3
  size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6e030f3d49ccdc1729e6f470b39b2ee25f4ac8236d75b80b3eae3c2d8d2c380
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc55474ec7083ec768bafb01ae9c71c99047535acdcbefdabead066d414d5f1
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae0ad2fdc6bac0e334b78d00b097e0bd9b9dd5ac6d4c56422df49dc386f92f4
3
  size 79431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994deb4a93f90da2b4fee4d4af87c5b9406751d3ea328ecc995da75cce552a2e
3
  size 79431
neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2dc1cd13f63d5609eae1c77ee53b11be787caeaf54b7f54db033d8d1f322af6
3
  size 318464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1588a7ea46d43352059bb8cdc393a447d1d1784af84f14251ceb80076511e713
3
  size 318464
neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:309ca07a8bf522d53c4f961ca1f8dc782cbbf51c8d928ffee3c42456ed6de287
3
  size 329762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec3a1886e11e568e658c14152e45db460a7a44b8fdfe83ff5d3dd864cd81e01
3
  size 329762
neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0f6d84e6afa880313f964ac2446d89f0fc1b78557f0afb0ea4197a9149c9f79
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa9f885f4efc918b827042f1c34badd68f9c844d90033d4730a878b3a4a9a0b
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:400b052a3001b05fc5c17bd5cf499fcf80afbd17eb21e1f1b1f9f92effba8931
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440323f4af46865bceb7408b37140a999b2e02a4745b6736e1adedb1cd5ff64e
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba5302b01ab44fb0bb3c86f3b9c0438d5f9d4be8f496501ed29ebb6ffdfb7923
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890ec6a0f753c9f9c9166051fe387da323ae33be211d724b810fbbbe8bc30282
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7534743372e1709951ddf865d8ac9e7fa5be14b954891c9ee8c5191fc3612fb
3
  size 68279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ace701a29dd40a20d0b86dc7d3c572990f7f98aaf5c97d77e8dd383bb4b465
3
  size 68279