Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
695
dacorvo HF Staff commited on
Commit
e84dffe
·
verified ·
1 Parent(s): 7fbee58

Synchronizing local compiler cache.

Browse files
Files changed (33) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/35bbdc163c6f0f272ac5.json +63 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/5971425e59d052eef4db.json +63 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/b97c760ba759013a2971.json +64 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/compile_flags.json +1 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/model.hlo_module.pb +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/compile_flags.json +1 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.done +0 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/compile_flags.json +1 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.done +0 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff +3 -0
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo +3 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/compile_flags.json +1 -0
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.done +0 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.hlo_module.pb +3 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff +3 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/compile_flags.json +1 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.done +0 -0
  22. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.hlo_module.pb +3 -0
  23. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff +3 -0
  24. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo +3 -0
  25. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/compile_flags.json +1 -0
  26. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.done +0 -0
  27. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.hlo_module.pb +3 -0
  28. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff +3 -0
  29. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo +3 -0
  30. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/compile_flags.json +1 -0
  31. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.done +0 -0
  32. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.hlo_module.pb +3 -0
  33. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff +3 -0
.gitattributes CHANGED
@@ -11455,3 +11455,12 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6095481617265815991+a3455b04/model.neff f
11455
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6318485788236650424+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
11456
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9054839121471829392+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
11457
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9935868010407306189+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
11455
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6318485788236650424+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
11456
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9054839121471829392+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
11457
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_9935868010407306189+a3455b04/model.neff filter=lfs diff=lfs merge=lfs -text
11458
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
11459
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff filter=lfs diff=lfs merge=lfs -text
11460
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11461
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff filter=lfs diff=lfs merge=lfs -text
11462
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
11463
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11464
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
11465
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
11466
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/35bbdc163c6f0f272ac5.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NxDNeuronConfig",
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
23
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
24
+ "continuous_batching": true,
25
+ "enable_bucketing": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 4,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.0.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 16,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 32.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": true,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/5971425e59d052eef4db.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NxDNeuronConfig",
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
23
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
24
+ "continuous_batching": true,
25
+ "enable_bucketing": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 4,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.0.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 16,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 32.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": true,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/b97c760ba759013a2971.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NxDNeuronConfig",
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
23
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
24
+ "continuous_batching": true,
25
+ "enable_bucketing": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "logical_nc_config": 1,
31
+ "max_batch_size": 4,
32
+ "max_context_length": 4096,
33
+ "max_topk": 256,
34
+ "n_active_tokens": 4096,
35
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
36
+ "on_device_sampling": true,
37
+ "optimum_neuron_version": "0.4.0.dev0",
38
+ "output_logits": false,
39
+ "pp_degree": 1,
40
+ "sequence_length": 4096,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn2",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 2
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 32.0,
54
+ "high_freq_factor": 4.0,
55
+ "low_freq_factor": 1.0,
56
+ "original_max_position_embeddings": 8192,
57
+ "rope_type": "llama3"
58
+ },
59
+ "rope_theta": 500000.0,
60
+ "tie_word_embeddings": true,
61
+ "unsloth_fixed": true,
62
+ "use_cache": true,
63
+ "vocab_size": 128256
64
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911e6e37d08b0e38efd539ec20caddc0e77d717bcaa800bcb88bacbd150d1e95
3
+ size 691139
neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1f8405558ed131fe9548c773e9b915c6dc96f676107cedda65b6a9cf969fba
3
+ size 1501213
neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1162607b2a3d5bc5dc6618cdc90bc8fdf46ee7e6179cba7e020de64bec652957
3
+ size 7363584
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6820471cc3742b4adf59a1b20142e67c937c1514499868f53f2b80d1077c6f62
3
+ size 418223
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8710ff580957991adbd175d321e516ded7ea97cccfc5dcd75cb1a9b0e64d227
3
+ size 3083264
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a556cd6fe4560e978200ecdd64beaa35ab3ee2614b2c5de61c387b997171e6
3
+ size 3157508
neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114e6541a2ea809b0dfc0aef23148d2ac33eaf99d7fdca3c6d6336946926504c
3
+ size 509380
neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ceeb73e1d39f204f2d5b6fe1d0f5f5ecea5529ce10edde0bdb5ee788508fd80
3
+ size 34100224
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317710548b5edeacc5f3f03a392a524bad93de31e8aad242ce4566c00177ff67
3
+ size 2531606
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6dc5299e05011fcdce1afa03aa5c7d1c38f45282ece45e7975388a88ddc43cc
3
+ size 4547584
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a389802593017b1c13fddddd315f9e7f14c2831be8ff6772155e94a48d113879
3
+ size 4622595
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d65c29e556d1756b32a9a888d1be21835118a660e141e6f7efca43108bdba2
3
+ size 1384595
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482163e936f7b99b7173234fc131b8db0258373b4421e060c1dcf22c7e6bdfbb
3
+ size 1106944
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d068abefa46de9fcd99296b16cbf7079ed25143381f8aac52dba12c33ecd19
3
+ size 1181044
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31cc4b21f5bf875f997fd77be46e7119d198bfad059866652176a4ceed7d8b2
3
+ size 1772495
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6cd561c58f1f4c424601de7845e388dab89adf40439586477138e5c4eded64
3
+ size 34612224