Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
dacorvo HF staff commited on
Commit
a5abf7c
•
1 Parent(s): 9926b84

Synchronizing local compiler cache.

Browse files
Files changed (18) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/10a67ce8876034703b65.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/35e204ec2c1ceb94bc9f.json +1 -0
  4. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/407e53aa03015f20f315.json +1 -0
  5. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/5d57584d9dc4d3c044a5.json +1 -0
  6. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/f24a583854b5a830a4d3.json +1 -0
  7. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/0727ce182e73ded6c583.json +1 -0
  8. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/08bad6e0aab77ca2ab06.json +1 -0
  9. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/12eef9821e8061459532.json +1 -0
  10. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/6ca93e4cda669432a91e.json +1 -0
  11. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/9f2d22000e1533e5c3f8.json +1 -0
  12. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/b7b0ba717dc778ceb108.json +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/compile_flags.txt +1 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/model.hlo.pb +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/model.neff +3 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/compile_flags.txt +1 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/model.hlo.pb +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1076,3 +1076,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff fi
1076
  neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1077
  neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1078
  neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1076
  neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1077
  neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1078
  neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1079
+ neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1080
+ neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/10a67ce8876034703b65.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/35e204ec2c1ceb94bc9f.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/407e53aa03015f20f315.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/5d57584d9dc4d3c044a5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/f24a583854b5a830a4d3.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/0727ce182e73ded6c583.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/08bad6e0aab77ca2ab06.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/12eef9821e8061459532.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/6ca93e4cda669432a91e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/9f2d22000e1533e5c3f8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/b7b0ba717dc778ceb108.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9f3791319f26ea429d15fddb5b64c7ca0f90967ec85bf1714b9df21022546a
3
+ size 350127
neuronxcc-2.12.68.0+4480452af/MODULE_2d1f5a44776c50690bd2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a317b8654b70f3e166e22b0429ac76d2cad79fd2a87e36bb181e7ae9c88d5ef9
3
+ size 8029184
neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b00206b3ef6099f059128b11f454c9b799d32fa11cb3f56f1b5757b30dbf34
3
+ size 394970
neuronxcc-2.12.68.0+4480452af/MODULE_8fe656895242178219e1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d6103b665d15a236ba2f3bcf62bc4a1450c80a74dc4ae01fc9139585c56b27
3
+ size 1936384