Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
250
dacorvo HF staff commited on
Commit
1ff4332
•
1 Parent(s): fb4018b

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 +46 -0
  2. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/0a57352c7fd763b555b2.json +1 -0
  3. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/2ef2288f29598787f90a.json +1 -0
  4. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/543d5a298da978bf2eea.json +1 -0
  5. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/6a2580f82abbca39b7e8.json +1 -0
  6. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/75b6ae752be0874692b5.json +1 -0
  7. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/7e85d17ae4dd9b3a2d88.json +1 -0
  8. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/8b6180d315737ae80d68.json +1 -0
  9. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/913714c63b99d90a6ae1.json +1 -0
  10. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/a461fa3d6df803f907a6.json +1 -0
  11. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/ab331eba159ded1807f7.json +1 -0
  12. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b9955896a71dfc78f28d.json +1 -0
  13. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/bf28cc6b9d14110257b6.json +1 -0
  14. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/f2c580dbc2713a5d9234.json +1 -0
  15. neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/model.hlo_module.pb +3 -0
  17. neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/model.hlo_module.pb +3 -0
  20. neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/model.hlo_module.pb +3 -0
  23. neuronxcc-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.hlo_module.pb +3 -0
  26. neuronxcc-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/model.hlo_module.pb +3 -0
  29. neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/model.hlo_module.pb +3 -0
  32. neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/model.hlo_module.pb +3 -0
  35. neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/model.hlo_module.pb +3 -0
  38. neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/model.neff +3 -0
  39. neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/compile_flags.txt +1 -0
  40. neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/model.hlo_module.pb +3 -0
  41. neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/model.neff +3 -0
  42. neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/compile_flags.txt +1 -0
  43. neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/model.hlo_module.pb +3 -0
  44. neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/model.neff +3 -0
  45. neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/compile_flags.txt +1 -0
  46. neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/model.hlo_module.pb +3 -0
  47. neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/model.neff +3 -0
  48. neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/compile_flags.txt +1 -0
  49. neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/model.hlo_module.pb +3 -0
  50. neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3259,3 +3259,49 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_291179394533923841+abb26765/model.neff filt
3259
  neuronxcc-2.13.66.0+6dfecc895/MODULE_8896680080935756983+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
3260
  neuronxcc-2.13.66.0+6dfecc895/MODULE_8968847275564604714+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
3261
  neuronxcc-2.13.66.0+6dfecc895/MODULE_9623917463913047246+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3259
  neuronxcc-2.13.66.0+6dfecc895/MODULE_8896680080935756983+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
3260
  neuronxcc-2.13.66.0+6dfecc895/MODULE_8968847275564604714+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
3261
  neuronxcc-2.13.66.0+6dfecc895/MODULE_9623917463913047246+abb26765/model.neff filter=lfs diff=lfs merge=lfs -text
3262
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3263
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3264
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3265
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3266
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3267
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3268
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3269
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3270
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3271
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3272
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3273
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3274
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_510d1b3e787db5d64500+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3275
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_53f2b9aee6106a9f4dcd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3276
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_5eda50b31e5c582e2878+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3277
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_6170b5f2281ca826c2b2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3278
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_667659b5880c8aa3c228+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3279
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_688776c29ec37ba82856+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3280
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_763de59456afcb367149+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3281
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_7a376947f78404875f58+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3282
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_7cf624dfa838c61f3c6b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3283
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_7e3464a9e0f1d4136a66+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3284
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_882ba05b08198c8f905e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3285
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_8fa8787f9d1cb78bf2ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3286
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_96197eb9bd55505ed7ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3287
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_968bf6eacaf5303d4c8e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3288
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_97b9e95fa2daba9493e8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3289
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_9b1aff5346a817ad5d9f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3290
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_9d1992f0aab64038d9c9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3291
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_a16cad38f886c688ecef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3292
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_aa23de623dd5e61f2b48+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3293
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_b62de3426c2cdf3bead4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3294
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_b99af071064810447719+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3295
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_b9bbef4437ef03c29568+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3296
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_bbc6a6451a22be51978b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3297
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_bcf852ae9f12d5ae27f8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3298
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_c1086afddb9cd4007def+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3299
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_cb2eb76a11d88856d152+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3300
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_d2a5e6fd24b065f29396+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3301
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_d3c9c5fa2608e9fa1b87+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3302
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_e4be7b4851b279b21c24+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3303
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_e774925ef02cac9260be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3304
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_e9cd7823552b4052fd1f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3305
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_f06eb185da899bd94560+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3306
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_f5782d94847d0a80b7d3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3307
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_fdf13076ef71fca7878d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/0a57352c7fd763b555b2.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": 24, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/2ef2288f29598787f90a.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": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/543d5a298da978bf2eea.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": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/6a2580f82abbca39b7e8.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": 32, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/75b6ae752be0874692b5.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": 24, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/7e85d17ae4dd9b3a2d88.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": 30, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/8b6180d315737ae80d68.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": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/913714c63b99d90a6ae1.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": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/a461fa3d6df803f907a6.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": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/ab331eba159ded1807f7.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": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/b9955896a71dfc78f28d.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": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/bf28cc6b9d14110257b6.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": "2.14.182.0+a56cbff7", "num_cores": 8, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/f2c580dbc2713a5d9234.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": 48, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "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-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1566e2a8f5b730de18b31d6d8d7c7c419cada8646df6cdc8cc6005fc2a186d3
3
+ size 310640
neuronxcc-2.14.182.0+a56cbff7/MODULE_0687095f8d3aa3ce12d6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea92cac7ab1c517d5daf84b871358b2edbf3c6d2fca7982a32a5296b8285b197
3
+ size 2253824
neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c7c74a97521977d7544dcae68780c86710b471b75a7727dc6e3804425b245d
3
+ size 499775
neuronxcc-2.14.182.0+a56cbff7/MODULE_0f8217c0f77d3545d502+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5339e95375d6b462904e4aa55975deab7a212a0608aad243e69fdaa3dd855637
3
+ size 31540224
neuronxcc-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/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-2.14.182.0+a56cbff7/MODULE_17fbd51961c885174794+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8668be9d590a9d2a55047b41a21999695397d9e923ac2aaa3471bfd500d3e7b
3
+ size 1803264
neuronxcc-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/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-2.14.182.0+a56cbff7/MODULE_1fc52214ed4eaafa2af7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aded78a224bafc3dc2856309060b388f04e766fe9b0dd310b309bf9e1803b97
3
+ size 1854464
neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24dac2e5442b3b3a4a7b785e652fa0ecfc8f4d370a56a0f3809651dcc4825474
3
+ size 399042
neuronxcc-2.14.182.0+a56cbff7/MODULE_25a6a99cc992600183b5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf991c2097a0abc00903d5e2bb43a6b0e3f528f3a53c737f0ca68d4860e8cea
3
+ size 13159424
neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa9b0014881a072b233e59c5afbde2120344a511174871b1f69394a80e8a2e3
3
+ size 316897
neuronxcc-2.14.182.0+a56cbff7/MODULE_2b1d09ca8c5308643fda+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a0bd7ca3345e013a7daae38a1a52b812c7daf2e04d7c8e54b896829ef2ae28
3
+ size 2305024
neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926c3024190b4c30509cf9806c8ea3b153a9dc78ed5ba1dec2a6c859a8bd43fc
3
+ size 499775
neuronxcc-2.14.182.0+a56cbff7/MODULE_2d3672e10ea0b9d9c314+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6980ca6fff904b34a1f3f1a4100f37ecc79a1463066b9c93e8e6cd492eaf1255
3
+ size 31540224
neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cb6ebdf0a6be648ca94f9bf518b59169aaaaa328a32295a74c3db8b0ca2088
3
+ size 312642
neuronxcc-2.14.182.0+a56cbff7/MODULE_2eb386754e54d4bd0df2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbed442c9eb1e5f33a97e2cf9f2ea2d08e501ea87c4ec9355a0671b56131513
3
+ size 2806784
neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102e7a2491f09e10ef994632cf15fb427df7abad5957822356aa76eae8b55cab
3
+ size 399298
neuronxcc-2.14.182.0+a56cbff7/MODULE_3a6b6d9e762081dec573+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2feb5d4a3efd90159fae8c389d92984344d15d4d7b96b59cea0db1a77e298f05
3
+ size 3625984
neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d928706f3b1ec7e521cae55f5911eb92fc44f684cff4bf6a3ba7dbcf5b4e3dff
3
+ size 399042
neuronxcc-2.14.182.0+a56cbff7/MODULE_3dbfc17c978392dd65eb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88ebd1aab7f1f27e575d58d436cfc0f6cef09a22ef82862816163d1eecd2020
3
+ size 4199424
neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1de16bf061ebedea621de088148b64b0fb34bb1cb05a14840d02b36a264f5e1
3
+ size 310640
neuronxcc-2.14.182.0+a56cbff7/MODULE_428a161fba1e6e515a29+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240cc11a83015d2dbb922b1f8c7282e3ed7d5ea7cc2a5e165c8979157da0bbae
3
+ size 2335744
neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46325e72cb58c370e3a948fda2c775a97147a05d05806f6e16b3ba38eb472eb
3
+ size 500031
neuronxcc-2.14.182.0+a56cbff7/MODULE_4c6bece225fa6802237c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a069236467e98b9149c6766d389cd49f1634ae4e70ba6149df4fa7a1f922c6a
3
+ size 26287104