Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
optimum-internal-testing-user commited on
Commit
9a0acc9
·
verified ·
1 Parent(s): c55ae75

Synchronizing local compiler cache.

Browse files
Files changed (39) hide show
  1. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/1c47516e348b0080b7ed.json +51 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2c6c957cbecbdedc94b7.json +51 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b6dd89dc8e8c479f4576.json +51 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/d16bc40bb3dc1c167f70.json +55 -0
  5. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/efca24f0b7490510c0e6.json +55 -0
  6. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/fc8d179e7140ee33b335.json +55 -0
  7. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/0dd0f622682ae91f9642.json +52 -0
  8. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/15ffb79712a794d020df.json +52 -0
  9. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/d736bde3bef7c455ed16.json +52 -0
  10. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/584f4046605bb1178573.json +49 -0
  11. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/3c4c1bf91d0e2598d844.json +53 -0
  12. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/617cc74c597aa72e7282.json +53 -0
  13. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/cd451ed66b6dc5957009.json +53 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff +1 -1
  15. neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +1 -1
  16. neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +1 -1
  17. neuronxcc-2.17.194.0+d312836f/MODULE_2e229618015e416964c5+613edded/model.neff +1 -1
  18. neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff +1 -1
  19. neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +1 -1
  20. neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff +1 -1
  21. neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff +1 -1
  22. neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff +1 -1
  23. neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff +1 -1
  24. neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +1 -1
  25. neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff +1 -1
  26. neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff +1 -1
  27. neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff +1 -1
  28. neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff +1 -1
  29. neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff +1 -1
  30. neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff +1 -1
  31. neuronxcc-2.17.194.0+d312836f/MODULE_b9cbc3c9d2c2ba603243+613edded/model.neff +1 -1
  32. neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +1 -1
  33. neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +1 -1
  34. neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff +1 -1
  35. neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff +1 -1
  36. neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff +1 -1
  37. neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff +1 -1
  38. neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff +1 -1
  39. neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff +1 -1
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/1c47516e348b0080b7ed.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.dev3",
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.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2c6c957cbecbdedc94b7.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.dev3",
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.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b6dd89dc8e8c479f4576.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": "fp32",
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.dev3",
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.dev3/inference/llama/llamafactory/tiny-random-Llama-3/d16bc40bb3dc1c167f70.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": "fp32",
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": 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.dev3/inference/llama/llamafactory/tiny-random-Llama-3/efca24f0b7490510c0e6.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.dev3",
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.dev3/inference/llama/llamafactory/tiny-random-Llama-3/fc8d179e7140ee33b335.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.dev3",
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.dev3/inference/phi3/yujiepan/phi-4-tiny-random/0dd0f622682ae91f9642.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": "fp32",
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.dev3",
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.dev3/inference/phi3/yujiepan/phi-4-tiny-random/15ffb79712a794d020df.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.dev3",
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.dev3/inference/phi3/yujiepan/phi-4-tiny-random/d736bde3bef7c455ed16.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.dev3",
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.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/584f4046605bb1178573.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
+ "_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": 4,
24
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
25
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
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.dev3",
33
+ "output_all_logits": false,
34
+ "sequence_length": 4096,
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/yujiepan/qwen2.5-128k-tiny-random/3c4c1bf91d0e2598d844.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.dev3",
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.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/617cc74c597aa72e7282.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.dev3",
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.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/cd451ed66b6dc5957009.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": "fp32",
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.dev3",
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 sha256:6d594981e2da8b776c3c5a3eca2164c9f6fa6f0c449ac944452b14c94ddf0495
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdf54d86fdcd3d86091c120a254ebfa45b7c25e9edbc32214ffbea4f1cd24f9
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 sha256:6112eb7624714812b25dc2f55104031955ba212a83c290b3e87880f61ae48063
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6678930e2553711be7e7ec07df81dcdc1ac25201db91b95dff988ecb306db54e
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 sha256:816f6e2b2800b0dd18941740a24948cd8febc13e0f8e9f734cc9f5dc87ad41fa
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b03d1bec0ca26dbfa61edeb9a0b6c20fc307230b004aa3110ce5d195e1de8d1
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_2e229618015e416964c5+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c00d0a765d16ac43f8777ec70370ed0eb63025c6279a1392b1683dcafc30f11c
3
  size 1414144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77561d14f2ba68cdad517e301f9954a9256169d6797a140ea40f19203cd4e585
3
  size 1414144
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 sha256:95ab464c4cf288bbb4eddc39060737a10a606d9a1780f619bd1249e31e77841c
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e469db51375a251ce72ef6012c9c91c0189c0ba2a97714eff6ad183ef623cea1
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 sha256:0d72740519c6f1609852cbefc2ca9c47c9c430eac2d564c11fb3e01d62dacc11
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad4017993b844343b7d1609dfdba54414dede36cccbe151add0fd6fd2b52b40
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5c71c790f5cec922792760f98f020c80f8851e65d99cf2165fd2380ae3b9a07
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409cc7601e08d76b6beebe9326de6219c4894402c15511777953cd0b30ff7716
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:b76edbd85e8c2a4c9aa2e4f0a91f8a2d55f739330a4c09432d5068a8eb021e53
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e03dd2bf31f267c7d97d880c614f69d6e5609b12db0e15cef2e16d96b0b333
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5871a8f23388ad9e78e2f48f3ee955c4facce1a3f373c6980e68f9cbef93853f
3
  size 164864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f953be9c4b6737576e22f5f38a06aec25810ac5c19737756deb35485ec4b30e
3
  size 164864
neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c71f97d235636814f05e8d6047fbe743ddb7e6d20f90577c8d29be05e7689d
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fceab55f8209ced9a72f475588a7f1efde8e89424f147c6e89b0cfc422fac2c
3
  size 154624
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:c242498d423f976198e48db300828acb03aeac1809d796be2e6a923bfb44689c
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e5106dd8f88c01eb4a6a06d95f85b268d84431acec5afb1b7d7d7fc3f20109
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bda494af1d3d8fe727fd6f8b8632c99dae58cb97e60706daad7ed24c100aa459
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6195c725343f68bee043f742f3c673ceb432db496ee9cd97168b17e81b734bc
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca8e32f83811391c47229b37a069f3e04202bd0b8df874d0638d0c49241e93d5
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a68b5600b67bbb732b60c6cbff1d4e81683385b94779dc136044600927de4c3
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b759b85a480af8a95b47df41a132f4fa1e2dfc1b6ab7712662c40a6fec780fc
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72a3115bfe3b6767eee1eaed7d2475336d13069649651c4cb584d54ee0d6cc7
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08bb2544280493888a28c15041cacb76676e5b9d21b307ae93ea22ef42c55383
3
  size 164864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ab39b59887637b9fefbcb824a417b2c8cf9d00ddcde12bd203fe16d6062443
3
  size 164864
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:e752ea5ae2b54d831b1fc55412033f8dff078e031e897fe39065590d6e03562d
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c793f874fbec3cd184a19d22f1469e7de1d7266bf0649afb2b95704d4e57216f
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:ee0a64a5653b89693c7530e4b34af017b865b942035a891f7207dcf423e71b98
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e265a8306026bff3628d0af5bb16a3fbce06698550359a8859392eb7674118
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_b9cbc3c9d2c2ba603243+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a62c29d78a45af62d00e10ebdf678692fabfd0225eff5bc451a74293216149f
3
  size 18433024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f8708dfaefd3fab2550dc5f896b9ab563eea8b63f620126f722f9ae25f0d5e
3
  size 18433024
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 sha256:8ba4b9459507087b23f2b32a59c2f74aa3f276eb3086271e06f33469da50eee6
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c13e58f40e385552b95c4585b1ae107b804427ed3cc4298fca6046390c1351
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 sha256:83d8ed4b67f52eff815a0995be0d5bebfd3f0bba38f620285c070d49aafe2a5c
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e1e49f8eddff3ec2eaa08ed7522d10bc022899a5e95ee3cc00b8235c139034
3
  size 134144
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 sha256:8f0f168589b268c08c82db181fdbff49cf3f20bf34e3296f7624e4613eac63a1
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60062f4664321f9aea72326646dfcce35291151c2986837950aca81b7cc1a61c
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:b86686143e8adfba9c0d950a405e8a6c1934a227faa64b402e5457c5be1920b8
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8839c761e481bd081000850fba079e2b2aaaa7c4c764a6dc58125051a69a0d9
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 sha256:9bb26efff1778505dd7037f18d58acb0906f2c53b16f4c92262ac0b93fde5005
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8c716e0e274599919f42f07a40c9a8eac91919eb4198682abfdfa81905b124
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78ec86204ac598cb366d25c34dbbf5bce1d88312f385c12735beff3d15ee37a1
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3cfb0f55f4251ebeb3cba8dac5345ccea7f1fff933314eb534263e37b337dda
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b78a37c04af5640a6bd258a6eb5e82790e3771baf0e1a2e10073d7bb7c87bef8
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f43c5e22d6f4ce95b271936af871d00f5030eb297298a1c01289f09307e8fc
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e5df0a3f1e98520edadd58cfff703a85026324eda7c3e3a8b5bfb6612e6fd9
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70b007f186dccce6841359cc88093d7c4e514cdcc6c6a61f6572c69a882bd89
3
  size 154624