Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
147
dacorvo HF staff commited on
Commit
4239344
•
1 Parent(s): 4e5b97f

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 +34 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/9699616599829b48b4a5.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/db1d9051ff5698e52393.json +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/2a30c91813b1e7196f95.json +1 -0
  5. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6434dcc45c7c9439f30f.json +1 -0
  6. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/7e91caedb706bd96bd3a.json +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json +1 -0
  8. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/fd9b28c3749a3bbd30c5.json +1 -0
  9. neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/model.hlo_module.pb +3 -0
  11. neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/model.hlo_module.pb +3 -0
  14. neuronxcc-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/model.hlo_module.pb +3 -0
  17. neuronxcc-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/model.hlo_module.pb +3 -0
  20. neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/model.hlo_module.pb +3 -0
  23. neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/model.hlo_module.pb +3 -0
  26. neuronxcc-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.hlo_module.pb +3 -0
  29. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.hlo_module.pb +3 -0
  32. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.hlo_module.pb.lock +0 -0
  33. neuronxcc-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/model.hlo_module.pb +3 -0
  35. neuronxcc-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/model.hlo_module.pb +3 -0
  38. neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/model.neff +3 -0
  39. neuronxcc-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/compile_flags.txt +1 -0
  40. neuronxcc-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/model.hlo_module.pb +3 -0
  41. neuronxcc-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/model.neff +3 -0
  42. neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/compile_flags.txt +1 -0
  43. neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/model.hlo_module.pb +3 -0
  44. neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/model.neff +3 -0
  45. neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/compile_flags.txt +1 -0
  46. neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/model.hlo_module.pb +3 -0
  47. neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/model.neff +3 -0
  48. neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/compile_flags.txt +1 -0
  49. neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/model.hlo_module.pb +3 -0
  50. neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3386,3 +3386,37 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_3ee79106ae9bfc013100+2c2d707e/model.neff fi
3386
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7651246321963ddd5906+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3387
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ade80a2b19e816657dab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3388
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e1e4cdeee8e8e42ef9b0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3386
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7651246321963ddd5906+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3387
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ade80a2b19e816657dab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3388
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e1e4cdeee8e8e42ef9b0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3389
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3390
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3391
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3392
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3393
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3394
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3395
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3396
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3397
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3398
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3399
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3400
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3401
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3402
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_5ddb9c233d7c07c4b83e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3403
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_606e1ed5209ba86b600f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3404
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_64e06093d33a080bb222+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3405
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_667659b5880c8aa3c228+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3406
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6c1d37c6bbfb3ba83465+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3407
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_712f16088b92ce1552a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3408
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_7a376947f78404875f58+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3409
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_862db2bb1f4da5e95e09+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3410
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8ae58871e7bd6db4281f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3411
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_941adcb49c0b0f9430a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3412
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_a16cad38f886c688ecef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3413
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_b79befd674e052c44c9f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3414
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ce4004e47d7f9259e48d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3415
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cebc0d79dffdb4b073d7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3416
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cf27c4eb2bcac29fb7ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3417
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ddff37e03914d1e4cc1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3418
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_e5482971f7e49838a230+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3419
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_e774925ef02cac9260be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3420
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_eae40350bbf4ea1569ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3421
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ec7ce1cb59fb29fdc73b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3422
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f8a00a8cdaa177ccee23+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/9699616599829b48b4a5.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/db1d9051ff5698e52393.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/2a30c91813b1e7196f95.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6434dcc45c7c9439f30f.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/7e91caedb706bd96bd3a.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/fd9b28c3749a3bbd30c5.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff95035e476d55cb19ab6f04831b676160715c7ba56816bef2dd715f62de978d
3
+ size 337090
neuronxcc-2.14.227.0+2d4f85be/MODULE_0129170172f364916548+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d17fee8b81f0b1a9ee6c71dabc3552b6616c5a395b34b97db4a14f61c93e9aa
3
+ size 3513344
neuronxcc-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/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-2.14.227.0+2d4f85be/MODULE_0157f35eb303445e190f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db5f4e4ff0fb41ea2c0aa51f9da32b038d998b8eb0635fbcab0a8370a38aa75
3
+ size 2950144
neuronxcc-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/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-2.14.227.0+2d4f85be/MODULE_01cc804175cc5fb0e309+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dadd8d705ed9d61451880279b44436fb5abd9d041d6b90e9618a9147f590f63
3
+ size 3963904
neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21b4e04683b0ecb3052baa6c2f05c1f684e2f40d95a167aa502e0e442500f03
3
+ size 254881
neuronxcc-2.14.227.0+2d4f85be/MODULE_09f9384fda97faade242+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c53bac818c03b3c793c41613d5b40308c20d165c3f100ab9df66af5bcdd1b8ea
3
+ size 2182144
neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f62f3312bb3b755f884a1668727749d3edb7c62f5590aa3b004172869bc5b6
3
+ size 310896
neuronxcc-2.14.227.0+2d4f85be/MODULE_17fbd51961c885174794+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b267ba5da88500b41b89df63e92abe854e50731e0dcb566710114839f4705c37
3
+ size 1803264
neuronxcc-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/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-2.14.227.0+2d4f85be/MODULE_1d5c76706b604a934e43+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d81d1a2b6c9128f1f9f3c909c8dff0d0c6f7d839c6f023d57fbe47f009fd2bd
3
+ size 2386944
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b359f3a640fad8eb963b7fe1d12dbe1380b0bfd3a56e3ac07119c4d217d779
3
+ size 310896
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a937ee53b82284d3ed7aff05236e716e7b45577b1030731bbb2cf685e480ac2
3
+ size 1854464
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df1d44f0b7301fccee5b1311bb42c246185f9b33739c0de9d3fbc82dbb0f23e
3
+ size 337090
neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/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-2.14.227.0+2d4f85be/MODULE_21e3dcaee19883fe287e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d2bbf3ced346caeca9b387944857cc266b88dfb8fc2c6ca2c875bbcf2beae2
3
+ size 13579264
neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66452bc80c6804461bfe9ed58e8d59ba7106d79887919d1139972e51d33fd28f
3
+ size 254881
neuronxcc-2.14.227.0+2d4f85be/MODULE_24c094e5b8a7b8e26a59+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248d8d76e4a30688a0c48ab115764c4f66071105dd48582da7ab9567a3ffe428
3
+ size 3021824
neuronxcc-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/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-2.14.227.0+2d4f85be/MODULE_33719efab65aba8971de+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460463feb4e313823bb824da26e2566be4085337a55419a65ec4974c8ace19b3
3
+ size 3830784
neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7caf33af677e610fa453612d92d55000aafccd9b14c1bd123db271075d9e50d5
3
+ size 254881
neuronxcc-2.14.227.0+2d4f85be/MODULE_3448a997dcf7ffa8ce06+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec3576b030b6fb48ec55178a1056c3af50cd58313a1fdb5a91bf202862db943
3
+ size 2530304
neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd139da3e58ca2056b373f09ffbf8e773c93a76e58f75c55cbd26628da9d07f5
3
+ size 445757
neuronxcc-2.14.227.0+2d4f85be/MODULE_51b8528780dc9259618f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948f59aa59d651441150d47d706482cf1e8021cd4daad8056fda4408ef915bd6
3
+ size 31960064
neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86bc5dc29eeab6253e1b53adab0036033b35cf8a282f7eb9d965252cb13b244e
3
+ size 445757
neuronxcc-2.14.227.0+2d4f85be/MODULE_51fa2c5a5f3058eea401+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573f29e5cd81f542c64ce5854cdeb79386e8fd9ea5fe13f8cfa2f10b81d52982
3
+ size 31960064