Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF staff commited on
Commit
3c9a2d3
·
verified ·
1 Parent(s): 5f40ca6

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 +48 -0
  2. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/7560e48b8ccab7f8e283.json +1 -0
  3. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/7bedca11d8eef0f022b7.json +1 -0
  4. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/17c656c7abb64c7466dd.json +1 -0
  5. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/57089b23be0910d8cbc8.json +1 -0
  6. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6767790cca5f811d84f5.json +1 -0
  7. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/740ed7b654b7c18270dd.json +1 -0
  8. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/91b57a8edda1c1c3a3ce.json +1 -0
  9. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d93f0bb3e47016036365.json +1 -0
  10. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/f69d881a5f54838a96cb.json +1 -0
  11. neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-2.7B/65af25a07a9af664c36d.json +1 -0
  12. neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/model.hlo_module.pb +3 -0
  14. neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/model.hlo_module.pb +3 -0
  17. neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/model.hlo_module.pb +3 -0
  20. neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/model.hlo_module.pb +3 -0
  23. neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/model.hlo_module.pb +3 -0
  26. neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/model.hlo_module.pb +3 -0
  29. neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/model.hlo_module.pb +3 -0
  32. neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/model.hlo_module.pb +3 -0
  35. neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/model.hlo_module.pb +3 -0
  38. neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/model.neff +3 -0
  39. neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/compile_flags.txt +1 -0
  40. neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/model.hlo_module.pb +3 -0
  41. neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/model.neff +0 -0
  42. neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/compile_flags.txt +1 -0
  43. neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/model.hlo_module.pb +3 -0
  44. neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/model.neff +3 -0
  45. neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/compile_flags.txt +1 -0
  46. neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/model.hlo_module.pb +3 -0
  47. neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/model.neff +3 -0
  48. neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/compile_flags.txt +1 -0
  49. neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/model.hlo_module.pb +3 -0
  50. neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -401,3 +401,51 @@ neuronxcc-2.14.213.0+013d129b/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.neff fi
401
  neuronxcc-2.14.213.0+013d129b/MODULE_7651246321963ddd5906+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
402
  neuronxcc-2.14.213.0+013d129b/MODULE_ade80a2b19e816657dab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
403
  neuronxcc-2.14.213.0+013d129b/MODULE_3ee79106ae9bfc013100+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
401
  neuronxcc-2.14.213.0+013d129b/MODULE_7651246321963ddd5906+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
402
  neuronxcc-2.14.213.0+013d129b/MODULE_ade80a2b19e816657dab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
403
  neuronxcc-2.14.213.0+013d129b/MODULE_3ee79106ae9bfc013100+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
404
+ neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
405
+ neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
406
+ neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
407
+ neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
408
+ neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
409
+ neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
410
+ neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
411
+ neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
412
+ neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
413
+ neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
414
+ neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
415
+ neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
416
+ neuronxcc-2.14.213.0+013d129b/MODULE_35628e0e7065fd39f1c5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
417
+ neuronxcc-2.14.213.0+013d129b/MODULE_35d96999ee4913118e5e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
418
+ neuronxcc-2.14.213.0+013d129b/MODULE_37baed5161817467e45e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
419
+ neuronxcc-2.14.213.0+013d129b/MODULE_392abcf826a8895949c4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
420
+ neuronxcc-2.14.213.0+013d129b/MODULE_4db722886dbd5a0e90d3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
421
+ neuronxcc-2.14.213.0+013d129b/MODULE_4f822640d7fcf1269c2a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
422
+ neuronxcc-2.14.213.0+013d129b/MODULE_5ddb9c233d7c07c4b83e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
423
+ neuronxcc-2.14.213.0+013d129b/MODULE_697621df8336098e9fb7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
424
+ neuronxcc-2.14.213.0+013d129b/MODULE_712f16088b92ce1552a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
425
+ neuronxcc-2.14.213.0+013d129b/MODULE_7e1a306b8f44990e78be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
426
+ neuronxcc-2.14.213.0+013d129b/MODULE_822bf0763f23d1cc785a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
427
+ neuronxcc-2.14.213.0+013d129b/MODULE_88bb293cbec6b542e9b1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
428
+ neuronxcc-2.14.213.0+013d129b/MODULE_8a2412619fc03f78847e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
429
+ neuronxcc-2.14.213.0+013d129b/MODULE_8ae58871e7bd6db4281f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
430
+ neuronxcc-2.14.213.0+013d129b/MODULE_941adcb49c0b0f9430a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
431
+ neuronxcc-2.14.213.0+013d129b/MODULE_9434d1e41373f6a0341d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
432
+ neuronxcc-2.14.213.0+013d129b/MODULE_981bf151b4d4d1bfaba6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
433
+ neuronxcc-2.14.213.0+013d129b/MODULE_99e853ec7bc39799a1f7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
434
+ neuronxcc-2.14.213.0+013d129b/MODULE_a5ebe619cd15ee115b6b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
435
+ neuronxcc-2.14.213.0+013d129b/MODULE_b79befd674e052c44c9f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
436
+ neuronxcc-2.14.213.0+013d129b/MODULE_b90aa3def33709e0aece+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
437
+ neuronxcc-2.14.213.0+013d129b/MODULE_bc64d40e1427eab85ba8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
438
+ neuronxcc-2.14.213.0+013d129b/MODULE_bc9b64a5de7b4f5eae3a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
439
+ neuronxcc-2.14.213.0+013d129b/MODULE_ce4004e47d7f9259e48d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
440
+ neuronxcc-2.14.213.0+013d129b/MODULE_cebc0d79dffdb4b073d7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
441
+ neuronxcc-2.14.213.0+013d129b/MODULE_cf27c4eb2bcac29fb7ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
442
+ neuronxcc-2.14.213.0+013d129b/MODULE_d11a14fe0d09008357f2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
443
+ neuronxcc-2.14.213.0+013d129b/MODULE_d37372bb65f76ac89b24+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
444
+ neuronxcc-2.14.213.0+013d129b/MODULE_d3c1fe65e3a050366815+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
445
+ neuronxcc-2.14.213.0+013d129b/MODULE_dde109d51980e5534145+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
446
+ neuronxcc-2.14.213.0+013d129b/MODULE_ddff37e03914d1e4cc1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
447
+ neuronxcc-2.14.213.0+013d129b/MODULE_eae40350bbf4ea1569ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
448
+ neuronxcc-2.14.213.0+013d129b/MODULE_ec7ce1cb59fb29fdc73b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
449
+ neuronxcc-2.14.213.0+013d129b/MODULE_ed56de1578306228c0e9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
450
+ neuronxcc-2.14.213.0+013d129b/MODULE_f3c3e815bc8fb3c7b0a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
451
+ neuronxcc-2.14.213.0+013d129b/MODULE_f5819d12264aac7692e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/7560e48b8ccab7f8e283.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "885173e97ab8572b444f7db1290d5d0386e26816", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/7bedca11d8eef0f022b7.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "81fc25d402859151f907ad479b18070a3c5a3c11", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/17c656c7abb64c7466dd.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/57089b23be0910d8cbc8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6767790cca5f811d84f5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/740ed7b654b7c18270dd.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/91b57a8edda1c1c3a3ce.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d93f0bb3e47016036365.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/f69d881a5f54838a96cb.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5504, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-2.7B/65af25a07a9af664c36d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-2.7B", "checkpoint_revision": "2f157a0306b75d37694ae05f6a4067220254d540", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 20, "num_hidden_layers": 32, "num_key_value_heads": 20, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bda1c787c58a7c91b56f5c7bc8cffba94e94affe25ed93afd5e75f1b41e5ef
3
+ size 263042
neuronxcc-2.14.213.0+013d129b/MODULE_0157f35eb303445e190f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8707aff7a4548a17e4b1a9cdc0f731909a6f9661fc8c021aff486e777f6d012a
3
+ size 2950144
neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5178ed4ecb814449145b310b3b7c5f60238d21270b2cedd6725f9ebb17cc80aa
3
+ size 256609
neuronxcc-2.14.213.0+013d129b/MODULE_0176fb35e78494db681c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d72b028aa844df5430ef1e00dd6958aca2a52986f19fe1c3f23090c3116b9a
3
+ size 3748864
neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f9c7e6febf4b6937cf831c6ec7659ef5b065859fc687e36653a12472a9a257
3
+ size 360581
neuronxcc-2.14.213.0+013d129b/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73bdb0e4ba255c5efad14cd2396f9ec9e61cf8e80c3c9f028bee75885525917
3
+ size 3963904
neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069b6db549c78b0645211b900002a69c5a791edfeac2f850bb6b4544d10f6535
3
+ size 323888
neuronxcc-2.14.213.0+013d129b/MODULE_146077388d26b5450bf4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3399c960a5b7e3d5c77ee10c6474ae1729bc462a9969d33541632e7751d2909c
3
+ size 2653184
neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ddd0fa36baa1ffccb172c1a5e0c2af3a9aec90cf1a79ecbef7a9e747040e4a
3
+ size 333872
neuronxcc-2.14.213.0+013d129b/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb3389f28222e26edd1e762ecc770c7b09aeb038f831c6b845429bbf25045f1
3
+ size 2386944
neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d0cae17db1f3f34e3982dff35139cf4d2ce78c855cfa280486263850234f5f
3
+ size 350595
neuronxcc-2.14.213.0+013d129b/MODULE_1e7a2f7302fa2bde6e72+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51a18e1517e5810b1214528cb2547af00043d3313f42cd61a82e779a23784f2
3
+ size 3585024
neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13b522ad45166c5df2d2864c1eb75df2e240879c6db4533b22fec098ee634cf
3
+ size 266465
neuronxcc-2.14.213.0+013d129b/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3da95930a4625d028e4223d1acf870ecf01483fee18d7b12c0d0dd20a4e703
3
+ size 13579264
neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4765221484edc95f6b892f58d320d4640f81b80c34a882c4e96efab5208b14
3
+ size 325426
neuronxcc-2.14.213.0+013d129b/MODULE_298c803bdff39c3d92ed+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188c4e77e56f8578f751fe2819c365c94bf9782f40e3b5a282b73a68808861ce
3
+ size 34233344
neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8ee595e96ede06e08a1ff8f0fb0a8fa92f20c3e0b69a1c1e07452f872475b8
3
+ size 350595
neuronxcc-2.14.213.0+013d129b/MODULE_29fb2a5ae4896a78c559+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5038d968469d32789fb84f57eebc1a9a42d281fc03662548566a0d220cfb6228
3
+ size 6145024
neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c9163db0fcabd8c5baaa381b64b90b7cb9a63aa5a497c6666801bced2b885e
3
+ size 44451
neuronxcc-2.14.213.0+013d129b/MODULE_2b55711d93e1566cdd78+2c2d707e/model.neff ADDED
Binary file (400 kB). View file
 
neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2ab921c34bb717a4691d89c6ce8dd6964f182097f6a0ea187df455e3f62a5c
3
+ size 323888
neuronxcc-2.14.213.0+013d129b/MODULE_2f46e3e3a9cc37a9f386+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc63b96da126818f2442e0505ee541c3ce21fa1eee53458cc273db24ef8e943
3
+ size 2448384
neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f9714a849abc7a81c860cd24be5de76ad7c037cc74d9c2a225804e0c55e069
3
+ size 266465
neuronxcc-2.14.213.0+013d129b/MODULE_33719efab65aba8971de+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc2d5e4d5e98e43f31d9dd1d7ce01fbca9e7858994f586e81669cba0094a10a
3
+ size 3830784
neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae6fb8fd3c66e17e30fe2e19e2f8b2a8ae8f85d02519fb10b586606a9587c83
3
+ size 360718
neuronxcc-2.14.213.0+013d129b/MODULE_345116edd09879b7ebe4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b44ab0897f8d69f01746b53dac24042f0a1d2ef8ae347618dd722c0b23b1e1
3
+ size 10875904