Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
336
jburtoft commited on
Commit
e1b3292
·
verified ·
1 Parent(s): f6651ae

Synchronizing local compiler cache.

Browse files
Files changed (34) hide show
  1. .gitattributes +8 -0
  2. neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Llama-3.2-1B/54f0121ba5e9c6032e07.json +1 -0
  3. neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/compile_flags.json +1 -0
  4. neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.done +0 -0
  5. neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.hlo_module.pb +3 -0
  6. neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.neff +3 -0
  7. neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/compile_flags.json +1 -0
  8. neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.done +0 -0
  9. neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.hlo_module.pb +3 -0
  10. neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.neff +3 -0
  11. neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/compile_flags.json +1 -0
  12. neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.done +0 -0
  13. neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.hlo_module.pb +3 -0
  14. neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.neff +3 -0
  15. neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/compile_flags.json +1 -0
  16. neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.done +0 -0
  17. neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.hlo_module.pb +3 -0
  18. neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.neff +3 -0
  19. neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/compile_flags.json +1 -0
  20. neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.done +0 -0
  21. neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.hlo_module.pb +3 -0
  22. neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.neff +3 -0
  23. neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/compile_flags.json +1 -0
  24. neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.done +0 -0
  25. neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.hlo_module.pb +3 -0
  26. neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.neff +3 -0
  27. neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/compile_flags.json +1 -0
  28. neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.done +0 -0
  29. neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.hlo_module.pb +3 -0
  30. neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.neff +3 -0
  31. neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/compile_flags.json +1 -0
  32. neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.done +0 -0
  33. neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.hlo_module.pb +3 -0
  34. neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -5873,3 +5873,11 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_9e44d7c07ac3d3aa4c36+39f12043/model.neff fi
5873
  neuronxcc-2.15.128.0+56dc5a86/MODULE_fee73ce8dfd95ba47126+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5874
  neuronxcc-2.15.128.0+56dc5a86/MODULE_45570346d414d5358482+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5875
  neuronxcc-2.15.128.0+56dc5a86/MODULE_64c0d9f2f7bce6f48dde+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
5873
  neuronxcc-2.15.128.0+56dc5a86/MODULE_fee73ce8dfd95ba47126+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5874
  neuronxcc-2.15.128.0+56dc5a86/MODULE_45570346d414d5358482+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5875
  neuronxcc-2.15.128.0+56dc5a86/MODULE_64c0d9f2f7bce6f48dde+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5876
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5877
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5878
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5879
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5880
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5881
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5882
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5883
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Llama-3.2-1B/54f0121ba5e9c6032e07.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "NousResearch/Llama-3.2-1B", "checkpoint_revision": "a9745ffc3556f145a830ac0c203509ba860582a3", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6add5d4178acd6bd44c595525d5c2cfc68bddc93f650abcfade03448ad263ea
3
+ size 128217
neuronxcc-2.15.128.0+56dc5a86/MODULE_28bbee103fa349000994+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f912c3e4469add4a429e4681ca5a0cbf42609f3e15a5ed7902deb501accba14e
3
+ size 2038784
neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638f6e4774811f7e52c908b525313e55596b332a388c4ae043a1148818b757fe
3
+ size 128217
neuronxcc-2.15.128.0+56dc5a86/MODULE_557c6f08fac3fa15f517+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e0b16288bc0ccf5352167d907b65cb8b407cdc9a2c46fe653d893c4fb0d4f5
3
+ size 1393664
neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c54ebdcc7728297417bc6bdc28ce634889cc04bf43ec83bea0201b88b2febe
3
+ size 126426
neuronxcc-2.15.128.0+56dc5a86/MODULE_56b46ebdee0801bc6f9d+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe5a8cd8230500ba7ebafa94dfb2edd1e8b77a14261f203c3dd47c7ef0bad71
3
+ size 1557504
neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73af1aa692fdc898383dbff293a5dbc9b0fa409eff5fd1aa54cfe31fc1038148
3
+ size 165606
neuronxcc-2.15.128.0+56dc5a86/MODULE_5d7f0a83b1473fb6e776+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4986ca9b3ec986614c358ebde556350624dd2fd7ce56beaeef27b02e8480a5c
3
+ size 1362944
neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1633cf904f95b0038ce013992c4a145650d07f447ac602aa4dc1259bfe473a71
3
+ size 165606
neuronxcc-2.15.128.0+56dc5a86/MODULE_a2ae2f2db38b798073f5+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7684a65d02bc97bea56e6b8bfa3fabf4536165b25160f4e12314eeaa51628dc3
3
+ size 1373184
neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4b2301092efdfcb1398da7286965264ad08d4438c4dd1c5110f45e6a65b1fd
3
+ size 128217
neuronxcc-2.15.128.0+56dc5a86/MODULE_b64b1c1fb64d7dbc13cf+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a5ae12bf47957d8fa6bf31960a817ba5e0b31a621d0a7a46293db44c11241c
3
+ size 1721344
neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b1cdb7f1e25dfd80eed1e3e599693a7244a29749c6dcda518ed7509e10a391
3
+ size 165606
neuronxcc-2.15.128.0+56dc5a86/MODULE_b9237b79a3daf9d1a318+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589504b45cc56f00814a7391f5d36cbf69f453834d8fdd61be42115d3c4b06dc
3
+ size 1403904
neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cc1a385fe0e918eb4e9ac2d19bb519a0b6258008da18143498b556e3578ff7
3
+ size 165606
neuronxcc-2.15.128.0+56dc5a86/MODULE_c22f48d42f730cf07e02+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7163be99e5def3f2560539c1194850dcb48ae6a6e30847f85cc5b0726d0f5830
3
+ size 1383424