Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF staff commited on
Commit
f0fb6bc
·
verified ·
1 Parent(s): d700576

Synchronizing local compiler cache.

Browse files
Files changed (49) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B-instruct/0371fe78d8117b0af5aa.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/26a049a1ffcf2c44be3f.json +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/ee7617214dccb41a3d74.json +1 -0
  5. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/335f8d1c7218c7410000.json +1 -0
  6. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/5e85017623f935a5084e.json +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/HuggingFaceTB/cosmo-1b/00271b4df65a1d15b20b.json +1 -0
  8. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-instruct/0371fe78d8117b0af5aa.json +1 -0
  9. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/0230aad0378abcb00404.json +1 -0
  10. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/26a049a1ffcf2c44be3f.json +1 -0
  11. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/ee7617214dccb41a3d74.json +1 -0
  12. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/61020f8e5609db4df382.json +1 -0
  13. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/864bc63eecc707804124.json +1 -0
  14. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/cc7cda3941881c035cb2.json +1 -0
  15. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/e31ae96d70b5049c0036.json +1 -0
  16. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/llama/NousResearch/Llama-2-7b-chat-hf/269c396ec83481c2a3e8.json +1 -0
  17. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/gpt2/gpt2/d5e93094d604b84cb59a.json +1 -0
  18. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/llama/HuggingFaceTB/cosmo-1b/00271b4df65a1d15b20b.json +1 -0
  19. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/mistral/optimum/mistral-1.1b-testing/3f196a5a5beadf2af838.json +1 -0
  20. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/compile_flags.txt +1 -0
  21. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.hlo_module.pb +3 -0
  22. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff +3 -0
  23. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/compile_flags.txt +1 -0
  24. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.hlo_module.pb +3 -0
  25. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff +3 -0
  26. neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/compile_flags.txt +0 -0
  27. neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/model.hlo_module.pb +3 -0
  28. neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/model.neff +0 -0
  29. neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/compile_flags.txt +0 -0
  30. neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/model.hlo_module.pb +3 -0
  31. neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/model.neff +0 -0
  32. neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/compile_flags.txt +1 -0
  33. neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.hlo_module.pb +3 -0
  34. neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.neff +3 -0
  35. neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/compile_flags.txt +1 -0
  36. neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/model.hlo_module.pb +3 -0
  37. neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/model.neff +0 -0
  38. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/compile_flags.txt +1 -0
  39. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/model.hlo_module.pb +3 -0
  40. neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/model.neff +0 -0
  41. neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/compile_flags.txt +1 -0
  42. neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/model.hlo_module.pb +3 -0
  43. neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/model.neff +0 -0
  44. neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/compile_flags.txt +1 -0
  45. neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/model.hlo_module.pb +3 -0
  46. neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/model.neff +0 -0
  47. neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/compile_flags.txt +1 -0
  48. neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.hlo_module.pb +3 -0
  49. neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -147,3 +147,7 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_e805a82c8d8a8e7ebfe1+2c2d707e/model.neff fi
147
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e8c6961fde56ab09a360+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
148
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f217aeeb232d7d4568c8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
149
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f4f63b2510413deb054c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
147
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e8c6961fde56ab09a360+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
148
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f217aeeb232d7d4568c8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
149
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f4f63b2510413deb054c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
150
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
151
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
152
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
153
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B-instruct/0371fe78d8117b0af5aa.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-instruct", "checkpoint_revision": "c4a54320a52ed5f88b7a2f84496903ea4ff07b45", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/26a049a1ffcf2c44be3f.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, "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": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/ee7617214dccb41a3d74.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, "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": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/335f8d1c7218c7410000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/5e85017623f935a5084e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/HuggingFaceTB/cosmo-1b/00271b4df65a1d15b20b.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": 8192, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "HuggingFaceTB/cosmo-1b", "checkpoint_revision": "0d5e341cfe835dffc81b6186f9715c094889f8ce", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-instruct/0371fe78d8117b0af5aa.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-instruct", "checkpoint_revision": "c4a54320a52ed5f88b7a2f84496903ea4ff07b45", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/0230aad0378abcb00404.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, "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": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 8192, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/26a049a1ffcf2c44be3f.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, "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": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/ee7617214dccb41a3d74.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, "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": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/61020f8e5609db4df382.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": "f16", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/864bc63eecc707804124.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/cc7cda3941881c035cb2.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/gpt2/openai-community/gpt2/e31ae96d70b5049c0036.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/llama/NousResearch/Llama-2-7b-chat-hf/269c396ec83481c2a3e8.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": 2, "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "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": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/gpt2/gpt2/d5e93094d604b84cb59a.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/llama/HuggingFaceTB/cosmo-1b/00271b4df65a1d15b20b.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": 8192, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "HuggingFaceTB/cosmo-1b", "checkpoint_revision": "0d5e341cfe835dffc81b6186f9715c094889f8ce", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/mistral/optimum/mistral-1.1b-testing/3f196a5a5beadf2af838.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "optimum/mistral-1.1b-testing", "checkpoint_revision": "ce03bc8d47dbd2c173ff65f3a8de1325ba724195", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd01968bc67569a3561bdf1099223fb5516fb5714ed5f7466120812a39e61d3
3
+ size 304356
neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6001419e0728084f193692681689a61ef0cb9f1df3844090cfb1426e32f6c111
3
+ size 14152704
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53a17bbbf8f685b9975fdde0af7d974f42e139fc3bd06266377687b58b4aeb1
3
+ size 316131
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97600f85c3771b92b591d7c1c71e69a8e090937e899b7fdf3eb298c596b5783
3
+ size 8786944
neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/compile_flags.txt ADDED
File without changes
neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b853f193ef2bd9688cfcc8221ea232cd741edeb111f4f8b88f138e6ef123f5
3
+ size 1387
neuronxcc-2.13.66.0+6dfecc895/MODULE_14817202047241907077+d41d8cd9/model.neff ADDED
Binary file (42 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/compile_flags.txt ADDED
File without changes
neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c8a140822e247f4d687006bd62adea2102570f109631b1dabdc1be955414e2
3
+ size 1389
neuronxcc-2.13.66.0+6dfecc895/MODULE_14887529043961575925+d41d8cd9/model.neff ADDED
Binary file (31.7 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91bd6687d96fd9da23d42613d7c9c2540e8bfa8529e1816ae71022fdb8e8e357
3
+ size 334991
neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198f028517f4e4cdf4ed2b7a540beeeefb6de5e7f9d3d328a9473e91cd7902ec
3
+ size 20337664
neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b950062b7cfaa616e259fa3c1f906e51d25fb0202306fbba8a8601f5fe1c2b93
3
+ size 132432
neuronxcc-2.13.66.0+6dfecc895/MODULE_2048325b90a23d2e3652+2c2d707e/model.neff ADDED
Binary file (462 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810a0032d065493481a13b4f00c936c0fbd29e192bc313bf54ea16d59efd6d25
3
+ size 132432
neuronxcc-2.13.66.0+6dfecc895/MODULE_3b335e5220018fa97c12+2c2d707e/model.neff ADDED
Binary file (503 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a65025636f9987503fbe2f400240c4e015507418a055731ed4602b6f05709a4a
3
+ size 132432
neuronxcc-2.13.66.0+6dfecc895/MODULE_4516146e45791c8ca05f+2c2d707e/model.neff ADDED
Binary file (441 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49492c8ede4d6bdf9f55433c92b649a417dbc1781b8a967e47ffda9d89f4123d
3
+ size 132432
neuronxcc-2.13.66.0+6dfecc895/MODULE_814c8003fc2d334f2fee+2c2d707e/model.neff ADDED
Binary file (472 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540b459d3d195150bc293dd41c5957320492eb536cf0d4b46a859d216720f8bf
3
+ size 379995
neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724b06c46dffda7a8b5a7318dd124989543d6f4b56a7a6bf418b5533025a2924
3
+ size 13200384