Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF Staff commited on
Commit
490c805
·
verified ·
1 Parent(s): 4cb12b9

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. .gitattributes +6 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/46592604b62f7ce89082.json +51 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6517782804be0be5e2a4.json +51 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/bb0a40e5cbe4d1c25285.json +51 -0
  5. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/bfc3e6553a3d02bc5c75.json +77 -0
  6. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/ce0df42e903c9a49fa72.json +77 -0
  7. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/llama/meta-llama/Llama-3.2-1B-Instruct/ab418e732245677e7cd5.json +77 -0
  8. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/291ed174890a84141720.json +73 -0
  9. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/41afd2fb7f6326db0c2c.json +73 -0
  10. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/650d381736581bd669c9.json +73 -0
  11. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/93956a41cd1203f773ff.json +52 -0
  12. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/b6837f9627ec2b9693be.json +52 -0
  13. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/dcd70056fa539895bb43.json +52 -0
  14. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/3ffe53335773a02926b2.json +53 -0
  15. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/af69549e13162a34952b.json +53 -0
  16. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/be422824e6f4d14a5909.json +53 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff +1 -1
  18. neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff +1 -1
  19. neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff +1 -1
  20. neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff +1 -1
  21. neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +1 -1
  22. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb +1 -1
  23. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff +1 -1
  24. neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo +1 -1
  25. neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff +1 -1
  26. neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff +1 -1
  27. neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff +1 -1
  28. neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +1 -1
  29. neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff +1 -1
  30. neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/compile_flags.json +1 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.done +0 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.hlo_module.pb +3 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.neff +3 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff +1 -1
  35. neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff +1 -1
  36. neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff +1 -1
  37. neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/compile_flags.json +1 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.done +0 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.hlo_module.pb +3 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.neff +3 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/wrapped_neff.hlo +3 -0
  42. neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff +1 -1
  43. neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +1 -1
  44. neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff +1 -1
  45. neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff +1 -1
  46. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb +1 -1
  47. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff +1 -1
  48. neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo +1 -1
  49. neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff +1 -1
  50. neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff +1 -1
.gitattributes CHANGED
@@ -2723,3 +2723,9 @@ neuronxcc-2.17.194.0+d312836f/MODULE_7d0c7e211138c3505935+165e9558/wrapped_neff.
2723
  neuronxcc-2.17.194.0+d312836f/MODULE_a1d42723f4b151570208+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2724
  neuronxcc-2.17.194.0+d312836f/MODULE_fdd1d8e95911bdcc8dec+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2725
  neuronxcc-2.17.194.0+d312836f/MODULE_fdd1d8e95911bdcc8dec+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
2723
  neuronxcc-2.17.194.0+d312836f/MODULE_a1d42723f4b151570208+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2724
  neuronxcc-2.17.194.0+d312836f/MODULE_fdd1d8e95911bdcc8dec+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2725
  neuronxcc-2.17.194.0+d312836f/MODULE_fdd1d8e95911bdcc8dec+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2726
+ neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2727
+ neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2728
+ neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2729
+ neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2730
+ neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2731
+ neuronxcc-2.17.194.0+d312836f/MODULE_fffbb7a74f126b7cac4f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/46592604b62f7ce89082.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.dev7",
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.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6517782804be0be5e2a4.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.dev7",
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.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/bb0a40e5cbe4d1c25285.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.dev7",
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.dev7/llama/llamafactory/tiny-random-Llama-3/bfc3e6553a3d02bc5c75.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": 128,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 128,
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.dev7",
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": 128,
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.dev7/llama/llamafactory/tiny-random-Llama-3/ce0df42e903c9a49fa72.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": 1024,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 1024,
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.dev7",
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": 1024,
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.dev7/llama/meta-llama/Llama-3.2-1B-Instruct/ab418e732245677e7cd5.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/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": "NxDNeuronConfig",
20
+ "async_mode": false,
21
+ "attn_kernel_enabled": false,
22
+ "batch_size": 4,
23
+ "capacity_factor": null,
24
+ "cc_pipeline_tiling_factor": 2,
25
+ "checkpoint_id": "meta-llama/Llama-3.2-1B-Instruct",
26
+ "checkpoint_revision": "9213176726f574b556790deb65791e0c5aa438b6",
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": 4,
37
+ "max_context_length": 4096,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 4096,
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.dev7",
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": 4096,
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": 32,
62
+ "num_hidden_layers": 16,
63
+ "num_key_value_heads": 8,
64
+ "pretraining_tp": 1,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": {
67
+ "factor": 32.0,
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": true,
75
+ "use_cache": true,
76
+ "vocab_size": 128256
77
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/291ed174890a84141720.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.dev7",
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.dev7/mixtral/dacorvo/Mixtral-tiny/41afd2fb7f6326db0c2c.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.dev7",
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.dev7/mixtral/dacorvo/Mixtral-tiny/650d381736581bd669c9.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.dev7",
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.dev7/phi3/yujiepan/phi-4-tiny-random/93956a41cd1203f773ff.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.dev7",
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.dev7/phi3/yujiepan/phi-4-tiny-random/b6837f9627ec2b9693be.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.dev7",
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.dev7/phi3/yujiepan/phi-4-tiny-random/dcd70056fa539895bb43.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.dev7",
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.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/3ffe53335773a02926b2.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.dev7",
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.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/af69549e13162a34952b.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.dev7",
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.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/be422824e6f4d14a5909.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.dev7",
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 sha256:483cc3307d02e47a81b425a2b348507ea125562830bf11ef11b8e9176614a5b6
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2443e5ed87cd2321559cfc61edbc0d0b9aed79ea53c6020815a6e66e449c9823
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 sha256:721b582c9e3d677d1e7356cb8bf8bccbb7412056eafb188cf5b46e5f5a57f4d8
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a0de5187c4d21a70fc592e7463fa702440eaf3733fefda7365e1e676adcd34
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:f912e0ad529c1dc24ee1b4547ac0715c82afb234da288138b96fce745a38e092
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec26c8671cbe08f14ab6cd99fba65b639956bf7fc6958535f68e2795b92937a5
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 sha256:9d22a1e7b00f466d826c4068fcc9586a8a744618dd537fb27a5d48dba12d3584
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddbfd696a0ef85d93c9d3198ab829bdf6ccf964781bb6a275a60414915f2790
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:b27c224e28dc73ee6a1c8ccb9b7667a5733fea6cc3edde7aeb6e9bd4d1aef336
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3ca6387784cd649abf3757bb3844b1eb9736e252e40b1a4968c1ece1b1fb16
3
  size 144384
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:b26956657e4985d91f8a65c2e50a278598a7d81fe9ad261ec755ae4fafb48005
3
  size 68277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bf2f66151be606218b2925a0449dd7916f07d36581a3b3b5bbd31c71807ecb
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:f983ce860d6d5fae63828bc4b0765911a526a11c61dfc6cc1a818d60567591f5
3
  size 257024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c182ea56f8adaf519edd44ac24b026ae1b85469a1f83eacc00cf20faabcaf4c
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:f84d825086c4ff10dec4e4f41cbdde297d95f64d4cf72aeca48b9463bab0c383
3
  size 268322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62d214cf48465f4a0b90420bc898a8fd7f5f9a8dcb6370edcdcf87b44b719f0
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 sha256:77dc8a6a2e4730499bffe4a7c4ddfcbc83cb23360dc07cf8d982887bf849d0b3
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4aa452b0cdbab618fc46a764cba28672fece03e81d085eccbda181a1b57b1ab
3
  size 134144
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 sha256:7d4f25ebae7cb3e88441333237eda262b68a21cf2e36db1c4b765e21098368ae
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7ca0b813faff5c0762966a281a46cde181daebae6b2e6da86be772e748dac6
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 sha256:62acf3dbb3edda20b1ca398b9815e08bc88f7b8031e892c2c8b6e0eadedb4727
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8166c37217252f0baf51dbf17ac221fad45563e85dd6ba5929fc8a55b3dd8e
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 sha256:2ed41f1b981e9f0dafae215296a5fc24f70084bace6a19ae6012b7ab362c0f61
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e8943204962ee0818af6e9711dcb0ead3e19d18121061ed3bf339fda9db608
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:bac2106f714d76ad9204fbd35121868918c15d9050bdaf3c2afb5b50db8537fa
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e769f891bcdf52ba48bdf4d9cdc171f7ed5b3c7fa8e80d8b5142f02b0d9a39fb
3
  size 134144
neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a92994ede93768a306aba61f9ff65cc12fd693d6855af9e79912cacd24c53e8
3
+ size 81347
neuronxcc-2.17.194.0+d312836f/MODULE_6645541ff96113d8e1bb+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21c560d53bd91367776a6093faa716f98f4a46654b4e26f21d3f03aaf58b6f5
3
+ size 267264
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 sha256:5cfd34e58c445f08569b573f3ecadc8feeefa4952fb932d1a75ff750af6ec781
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89bae87420edb640dcdaf0058d4d072acc4dee3f5a7a0bc3e4bcb1e842cea2b1
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 sha256:2d6f95a7d6833dbe3393089435d052f75e29eb6ceaae03ed45f7c8484db314cc
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7da23595b827adb9d8b7a49fa9d5045523fe83ed5b0ea04059e93bac81a6388
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:a46dbe504a3da3305bc17e8a918fbd6b3dfed8e231fca1897661561e2b99ed67
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612bab8ae99ee0d23a9d65a92642ea53faedc02eac5be589301f340ecc12947e
3
  size 154624
neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d8908f9c41121c1355085a90259da1519666fd64cab6bc119930a495d28013
3
+ size 80893
neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfab6c5ec7ab6dafc649abcd5f9dff3c79bf3a2e3141853a22ed2759aac7f12a
3
+ size 246784
neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb963bbc7241580114f5297fd62fc3e8cb19377eb953deb673fb5999c37e8c3
3
+ size 254591
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 sha256:8a6690dd12f2574b84fa1bb885dfc0d5c8e404367a3c0543467273995955cf74
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47e234954a33ef3ab081870796384f1aeff31d539c4ffc08d234f774eab49a2
3
  size 103424
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:f4e4e69e199614930a4c72c1eb5005674e416a5565f4af5acdd6c718c5db75f2
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67d32a3ec490fd861d862971d7785f2b09b4d194a979085ca624e5d5d4c2ee1
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 sha256:64e0ad916cf7fee2927046f42d1a2894837ce6223a638bc1e9d6f49a0680dcad
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ab95be0675292eecd4b501ac040ebdc56436de5b667c1c8635b309be7968a4
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 sha256:16984937693e7ef0c5425dc19be823c273d12c6dae836a2b89e48f36192ffd76
3
  size 154624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030a86fef9f262d80476617fdba0b793965fed279d62c7e0b6a6766befde4626
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 sha256:41490d63779b527575e2162aff5fa91b3ed4cba95b2fd0e4204eaafa113eb759
3
  size 79431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f894bf1ee79204a45884e8a3af4127e518849e995cbf7e8d136700c1198843fa
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 sha256:1a44578f4e0aa4f000ca0cc620b75ac32619a659c12e1ae27846ce414dc2bb0f
3
  size 318464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d94fd1f20a72bcd3092ed00f14c78dd8622cc06a2d6343090e9de5d76513b74
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 sha256:06e51810e6dbf9633463d0bf3b533a3c6e6365923c6e96b2a836515d831506c5
3
  size 329762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7219d56c85106e3db6dc64691e64d0c47eef47e8d69b18d0d780f1e4efd4434
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 sha256:0653b6870382c6bbddba478c11df27a418861fae2fb51d7235e2a8d5592685a2
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7534f49d9e6d81d2ad3c7f3c0535230f910ac6ad0135fff8519cfc39ab1e29bf
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 sha256:705ad67c1257846117399f0857438a3ac6018074efc2b824f94e427c4ff726ed
3
  size 134144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977848c5fb76c6b48cf2a2c3d911d47366b76f1a23010177a494a420057b968d
3
  size 134144