Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
c970eaa
•
1 Parent(s): 4202972

Synchronizing local compiler cache.

Browse files
Files changed (18) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/22cbc5b9c134829fb965.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/8980de39a9f47d395f7b.json +1 -0
  4. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/9568d6462b44ee8f3b34.json +1 -0
  5. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/a0bbba65f0887dd19505.json +1 -0
  6. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/OpenAssistant/llama2-13b-orca-8k-3319/20d2823c7da1d74be70d.json +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/compile_flags.txt +1 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.hlo.pb +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.neff +3 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/compile_flags.txt +1 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.hlo.pb +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.neff +3 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/compile_flags.txt +1 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.hlo.pb +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.neff +3 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/compile_flags.txt +1 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.hlo.pb +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1048,3 +1048,7 @@ neuronxcc-2.12.68.0+4480452af/MODULE_9d0c68fb35a6420e7c4a+2c2d707e/model.neff fi
1048
  neuronxcc-2.12.68.0+4480452af/MODULE_b172e150ce0fdf2c21b9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1049
  neuronxcc-2.12.68.0+4480452af/MODULE_7c6d60bcc076f9581425+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1050
  neuronxcc-2.12.68.0+4480452af/MODULE_9a2d29923705165c2514+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
1048
  neuronxcc-2.12.68.0+4480452af/MODULE_b172e150ce0fdf2c21b9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1049
  neuronxcc-2.12.68.0+4480452af/MODULE_7c6d60bcc076f9581425+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1050
  neuronxcc-2.12.68.0+4480452af/MODULE_9a2d29923705165c2514+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1051
+ neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1052
+ neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1053
+ neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1054
+ neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/22cbc5b9c134829fb965.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, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f", "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/NousResearch/Llama-2-13b-chat-hf/8980de39a9f47d395f7b.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, "pad_token_id": 0, "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": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/9568d6462b44ee8f3b34.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, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-13b-chat-hf/a0bbba65f0887dd19505.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, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 8, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/OpenAssistant/llama2-13b-orca-8k-3319/20d2823c7da1d74be70d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32016, "max_position_embeddings": 8192, "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": {"factor": 2.0, "type": "linear"}, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "max_length": 8192, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "OpenAssistant/llama2-13b-orca-8k-3319", "checkpoint_revision": "b02bf240968a60674d9e1afc73f83868ae52fee0", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd559b62e9c0901676222ccabfab31bedc8293ae3141d9a8ae0f952329519151
3
+ size 437488
neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4df252c875cf39183daaf352a08f1a2231ea31a11b46555430c7dc20474991
3
+ size 13661184
neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe60059a69f792c2727c635a850fcee8a25c8926e239e54e9ac921cbb54e17f
3
+ size 436208
neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13d39805b91eaad1a28d522399cadbb356d1a572d667c0cd70525ba6a0a10d7
3
+ size 25467904
neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6bc696c4a0100291cfee880fb0f54a8fbb24c5768fa3bbfc9a6ade12d1c7529
3
+ size 492067
neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac848d03d1c7ce7de45b38bfbde9e3782aca9d8c7cd9424ad6cb821879299274
3
+ size 6482944
neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a16191d975f5e1645943c15ecc30324c22de5a73df77b2ff436a7cdf2e7a7cc
3
+ size 493347
neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83067176e3515d36a0d0a128e673c371995a5bb6547bdfa4e68805d1be762994
3
+ size 2898944