Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
255
dacorvo HF staff commited on
Commit
ab2d667
•
1 Parent(s): f899450

Synchronizing local compiler cache.

Browse files
Files changed (18) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/322dcdbc438eb4b96e11.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/3ebd53f4dcf186fb9525.json +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/66c0860435a88a980479.json +1 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.hlo_module.pb +3 -0
  11. neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.hlo_module.pb +3 -0
  14. neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.14.227.0+2d4f85be/MODULE_cf83f5b5494dc3bd20ce+2c2d707e/model.neff +3 -0
  16. neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/compile_flags.txt +1 -0
  17. neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.hlo_module.pb +3 -0
  18. neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3420,3 +3420,9 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_e774925ef02cac9260be+2c2d707e/model.neff fi
3420
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eae40350bbf4ea1569ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3421
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ec7ce1cb59fb29fdc73b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3422
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f8a00a8cdaa177ccee23+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
3420
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eae40350bbf4ea1569ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3421
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ec7ce1cb59fb29fdc73b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3422
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f8a00a8cdaa177ccee23+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3423
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3424
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3425
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3426
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3427
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cf83f5b5494dc3bd20ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3428
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/322dcdbc438eb4b96e11.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/3ebd53f4dcf186fb9525.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/66c0860435a88a980479.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/MODULE_1fef5a5f1f14da33eb81+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca9948ea77e6c46e24f860ca1df76870a7c88cbf2c27bf6b698961fa8dc87cd
3
+ size 4516864
neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf972470c11c377d6f5db68c0c60583af52b6b79f5996f3c11875eba97a46bb
3
+ size 434173
neuronxcc-2.14.227.0+2d4f85be/MODULE_24382d77bc5622e0f5a3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c062ce4da410dc1b72fd67a8ad3d8a1fdb233212d5a46054a30978a386ecb3
3
+ size 25191424
neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4599eb3d67ef49953f5bd5b6668c9e51a58122e6d2a40045dee6f439c012e3d2
3
+ size 337090
neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7684bd39648174f9256148d70049b57cb110590abf5aea83911b1887a3ce3747
3
+ size 8776704
neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c508e1979c448573542586ef7d9e343241ff64fcc54e448f6142707f76c527b
3
+ size 337090
neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de11f38d664aedb1e13cec401cc1aa2bb5abee01bb7931e6d1c37cb65b186ef
3
+ size 6575104
neuronxcc-2.14.227.0+2d4f85be/MODULE_cf83f5b5494dc3bd20ce+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0a67a64f5736cbedee35f4f7363dd464b36a5b6baf1006c857c98ed0a333ea
3
+ size 25191424
neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f4a905cef180184e8ca0d14be6031beaac6abcbc4ccb96ef2abfe8539efe0f
3
+ size 434173
neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0679b7c1b2a07a7f4f95c231130b2c3f711fc5018a768dad138c905e3fad761a
3
+ size 25191424