Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
ac28972
•
1 Parent(s): 27baeb2

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 +60 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/1ab4fec65fe40b15d8fc.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/0c05f781075e377b3fe0.json +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/5a8294b279e725cf8542.json +1 -0
  5. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/735e2b4b3a5019f203a7.json +1 -0
  6. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b4d9aa50677e27d82b4f.json +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b57ff0785cfe94aa0718.json +1 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/compile_flags.txt +1 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/model.hlo_module.pb +3 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/model.neff +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/compile_flags.txt +1 -0
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/model.hlo_module.pb +3 -0
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/model.neff +3 -0
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/compile_flags.txt +1 -0
  15. neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/model.hlo_module.pb +3 -0
  16. neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/model.neff +3 -0
  17. neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/compile_flags.txt +1 -0
  18. neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/model.hlo_module.pb +3 -0
  19. neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/model.neff +3 -0
  20. neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/compile_flags.txt +1 -0
  21. neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/model.hlo_module.pb +3 -0
  22. neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/model.neff +3 -0
  23. neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/compile_flags.txt +1 -0
  24. neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/model.hlo_module.pb +3 -0
  25. neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/model.neff +3 -0
  26. neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/compile_flags.txt +1 -0
  27. neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/model.hlo_module.pb +3 -0
  28. neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/model.neff +3 -0
  29. neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/compile_flags.txt +1 -0
  30. neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/model.hlo_module.pb +3 -0
  31. neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/model.neff +3 -0
  32. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/compile_flags.txt +1 -0
  33. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/model.hlo_module.pb +3 -0
  34. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/model.neff +3 -0
  35. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/compile_flags.txt +1 -0
  36. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/model.hlo_module.pb +3 -0
  37. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/model.neff +3 -0
  38. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/compile_flags.txt +1 -0
  39. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/model.hlo_module.pb +3 -0
  40. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/model.neff +3 -0
  41. neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/compile_flags.txt +1 -0
  42. neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/model.hlo_module.pb +3 -0
  43. neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/model.neff +3 -0
  44. neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/compile_flags.txt +1 -0
  45. neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/model.hlo_module.pb +3 -0
  46. neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/model.hlo_module.pb.lock +0 -0
  47. neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/compile_flags.txt +1 -0
  48. neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/model.hlo_module.pb +3 -0
  49. neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/model.neff +3 -0
  50. neuronxcc-2.13.66.0+6dfecc895/MODULE_486c7a82a8c022dff09d+2c2d707e/compile_flags.txt +1 -0
.gitattributes CHANGED
@@ -2443,3 +2443,63 @@ neuronxcc-2.13.68.0+6dfecc895/MODULE_8451101906021534154+55d6a20f/model.neff fil
2443
  neuronxcc-2.13.68.0+6dfecc895/MODULE_913272093888285008+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
2444
  neuronxcc-2.13.68.0+6dfecc895/MODULE_9613391693182017117+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
2445
  neuronxcc-2.13.68.0+6dfecc895/MODULE_9985841552596062342+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2443
  neuronxcc-2.13.68.0+6dfecc895/MODULE_913272093888285008+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
2444
  neuronxcc-2.13.68.0+6dfecc895/MODULE_9613391693182017117+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
2445
  neuronxcc-2.13.68.0+6dfecc895/MODULE_9985841552596062342+55d6a20f/model.neff filter=lfs diff=lfs merge=lfs -text
2446
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2447
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2448
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2449
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2450
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2451
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2452
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2453
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2454
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2455
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2456
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2457
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2458
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2459
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_486c7a82a8c022dff09d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2460
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_51e280213d3349f527d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2461
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_549172aa834892c7c7a4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2462
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_566eabca608aba464c36+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2463
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_5874976226b548eb5371+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2464
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6448de0d7cf065f478d5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2465
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6894a3560ccb6b65e95d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2466
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6ae1c452ac1fdada3eb2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2467
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6d21ace3022d34ab3830+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2468
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6e01e37e53f41097b6b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2469
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_76f7d0b68aec3cb69d0a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2470
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_78d21abaf2f2d060b22b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2471
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_7c1bb27bab9691eba531+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2472
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_7e2b745e708288a40519+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2473
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_7f81455f54f39113fb16+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2474
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_83df5e0a8e20244654ed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2475
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_856f02167205261ff8fc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2476
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_86cf0513653fad241ec3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2477
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_89f4ef99a1b9dc2e0376+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2478
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_8b5c27e70924272ec512+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2479
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_8e207a20e91d1dbf8a00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2480
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_8ffe5fc009f227ac2503+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2481
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_92a4f58f6236c561796c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2482
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_980f9018dc8fd109bdd2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2483
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a2682791cd350ba7a9fe+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2484
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a48e6804bafaa4e7ae79+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2485
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a75a2029ddf30ccd71c0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2486
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ae8b47db3e76c14c631a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2487
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_af2d0d551946d2440394+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2488
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_afc09ba31e52cb79957b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2489
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b2ff93897da9ae5d4230+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2490
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_bcd19bc67db1b3ff4381+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2491
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_c20d4048148f74bd831e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2492
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_c42d9fbc62e7ab02b883+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2493
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_c51d71779e7baf780bdd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2494
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ce35a7f50500ae68dabb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2495
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_daf677f1de2932b06dee+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2496
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e0428cac0a05340dd6b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2497
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e0aea0f1fae7e8ea75a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2498
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e662eba2c35ccc6d0e75+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2499
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e6eefadafc00e030357f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2500
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e8eb76aadbf870ef66cb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2501
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e927a8c1d5e1e8ef193c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2502
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ea3dcabd6c9634a1604e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2503
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_eb62436c86a87d12aabf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2504
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_eeb5873dd3e715b2c510+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2505
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_fba6a92254966a90eb3b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/1ab4fec65fe40b15d8fc.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": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/0c05f781075e377b3fe0.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/5a8294b279e725cf8542.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, "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": "2.13.66.0+6dfecc895", "num_cores": 24, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/735e2b4b3a5019f203a7.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, "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": "2.13.66.0+6dfecc895", "num_cores": 24, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b4d9aa50677e27d82b4f.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b57ff0785cfe94aa0718.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "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-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651742271c27e3721a66cc72c7e9f11b12d1f799e617d176f79559662ea26578
3
+ size 371259
neuronxcc-2.13.66.0+6dfecc895/MODULE_030e33ef5cbb962feaff+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28902f1884a5e127068e71762a083ded1a9b0e1c039d29daf6f67a12249dc8de
3
+ size 7353344
neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16459fcc2a1c86cfba250d4901050bb6648787e6f805b0edf061ecdf5f124463
3
+ size 300634
neuronxcc-2.13.66.0+6dfecc895/MODULE_080e84736415daff8ec2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71dd89cc6d4fc63b390e068500d43163378c930697cc757160d9d68d01749dbe
3
+ size 1291264
neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd505c607de6390cf3b8a126862c083a8ab007cb2cd942883299a76698f21283
3
+ size 336719
neuronxcc-2.13.66.0+6dfecc895/MODULE_0a5bc51ecf53ae664481+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a5cb0d1c5e44158ff65c346f6e9657115351c0859ac4dbca2e87ff5789bd2e
3
+ size 17193984
neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba8fb4e8c72e2af5f03448185330da0aa7aca9e6f20b7617e4c93ac5492552d
3
+ size 421309
neuronxcc-2.13.66.0+6dfecc895/MODULE_0b46584d966f73defc7f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8af71b6dc042988b40ca6ddebc2410af56126f066596c2e5f88b135e8889b0
3
+ size 4168704
neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd445c9b66fb6771ce2929e49c0b80c8e9a91bd6a5ddef299c6e38181964919
3
+ size 381723
neuronxcc-2.13.66.0+6dfecc895/MODULE_10b9bdbf2c308ea5cfd6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e28054c756f72ab289e264aae6a45a821be574fe2daf0ea67b5ceae4565b63
3
+ size 4066304
neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4531ba09afd7b78594a1b6b09ef336c3df931a865d4cba61f45c1e41ddc7a4bb
3
+ size 397595
neuronxcc-2.13.66.0+6dfecc895/MODULE_191faaea815817f18cbc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:284786819c30e41cdaa6b28f461ecb9736f976229fa94c75d58d332d9a006fc8
3
+ size 4086784
neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf70394505c59e0fce89e72a2ce531800e8e4fb09a75bf7767b65c339d7ded5
3
+ size 397595
neuronxcc-2.13.66.0+6dfecc895/MODULE_20ae17db0c2c9f8459be+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02e645ad56d26eb467ad56a81356e9dad0ff220797971cec312ecd621321565
3
+ size 6247424
neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a0ee7d4822263ee7b716c4adc4ecb394c1189f462d07f3104b4e1522b2dfd8
3
+ size 375515
neuronxcc-2.13.66.0+6dfecc895/MODULE_2ab662af1ee4f42104cc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfe2169e8aa30a6cad515c85cecb082d98a154a49866ec556662adf6bffec53
3
+ size 1967104
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd364110d3886e0ee0a96d5bf7c6315a629aacffed12fcdf49a5611109df22fa
3
+ size 375515
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b0708cd079253ab7760+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e4d53f580bf954ec3835e0102df1b3b6140ac7a95f7aac83eeeae8e9961df5
3
+ size 1895424
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ba00c294bb39f12971dc364afe7adb479f5d7b3155fb9ce12949fcc1de962a
3
+ size 336719
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f04dbee4ab2e153e3c7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b99e0169b8df8041ca7403ad61a45fb524770c0ed4b797c9b41f78cae86024
3
+ size 17193984
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51aaf988d2296218e4993687fca20634758e320651a2838a4b4bddcc25b8879f
3
+ size 300634
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f669e736d8907cd1111+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f707013a5b511194428339464a9f4092adb07ed998869adf358a75c67d6a526a
3
+ size 1373184
neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14820a0d9f6a075345f2c00e1b702e4d78ece4357ebebddf7d65447b4a9b3915
3
+ size 421309
neuronxcc-2.13.66.0+6dfecc895/MODULE_442eda90da2cf2f72c01+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071268e1d3d477c67089f35bd64635b543fd2ce8dedd6fcc3efce250fcdcc76a
3
+ size 4189184
neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6b6b5c6cf5a5d3fd013c6a44fce319e59cc1f578131d7e936bf85773bca1b7
3
+ size 420713
neuronxcc-2.13.66.0+6dfecc895/MODULE_443c7de81db84f0f078c+2c2d707e/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b543db457fa31e31d199a4ccf7987575d7932894e008ea208153eaa2414e119
3
+ size 344207
neuronxcc-2.13.66.0+6dfecc895/MODULE_475f0e6eb6f4502b945e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba46b1e3bab88ac5bbeb8f40a91585ca81ca93399bdc1c0a3c8fdb0a2a9e8b8
3
+ size 30096384
neuronxcc-2.13.66.0+6dfecc895/MODULE_486c7a82a8c022dff09d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none