Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
121
dacorvo HF staff commited on
Commit
a77b24d
•
1 Parent(s): 5ca795f

Synchronizing local compiler cache.

Browse files
Files changed (15) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/26575c75a97054312245.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d8d190c62c0b163c34d7.json +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/compile_flags.txt +1 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/model.hlo_module.pb +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/model.neff +3 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/compile_flags.txt +1 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/model.hlo_module.pb +3 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/model.neff +3 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/compile_flags.txt +1 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/model.hlo_module.pb +3 -0
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/model.neff +3 -0
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/compile_flags.txt +1 -0
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/model.hlo_module.pb +3 -0
  15. neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2581,3 +2581,7 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_99dde6c040cad2ae1788+2c2d707e/model.neff fi
2581
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a06c2a9fc81c978515e9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2582
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b3ca64867673612ad42c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2583
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5fae4eaeff8c4b088ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
2581
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a06c2a9fc81c978515e9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2582
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b3ca64867673612ad42c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2583
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5fae4eaeff8c4b088ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2584
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2585
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2586
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2587
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/26575c75a97054312245.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": 48, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "1460c22666392e470910ce3d44ffeb2ab7dbd4df", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 12, "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.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d8d190c62c0b163c34d7.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": 48, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "1460c22666392e470910ce3d44ffeb2ab7dbd4df", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "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/MODULE_1c4be4f9d056547195c3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2065288d3747c55ef1a1196aea598e0d95971591cb0bbbf698da63b2ba523b4c
3
+ size 335951
neuronxcc-2.13.66.0+6dfecc895/MODULE_1c4be4f9d056547195c3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50cdee652d05c688018b32c8ae92ea149c9b29ccb704b0acd70f5976ea5b51f1
3
+ size 25703424
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0bbcb4947a39c46831db7671e3214c8399f2bf9398e3ad1f678f7357c35c5f
3
+ size 380955
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6b5f55a1f4f693790c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed5626b91386311ab7c16f65b0ea49e8e0a739f579805f0cdec819661523b08
3
+ size 22232064
neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e5440b67f97a591b2a2d14df90941bb6397cd7d8d742e93c9d82fa4c2b9625
3
+ size 344207
neuronxcc-2.13.66.0+6dfecc895/MODULE_830f95f98361da5d8382+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2876219e9503f9ab585be35bee1ea44dcccee64f4fadb282ea17f63f5fddaf3
3
+ size 30096384
neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d03d447f05d71d5442c431307dd9b0ecd1418f806889d236fbd4b4928a6bd8
3
+ size 397595
neuronxcc-2.13.66.0+6dfecc895/MODULE_d1ba6c68e170415611b1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cb44cdfa533612bab5ce4c029260ed0cd174d3b28ee0030e7dc81524ed2342
3
+ size 8049664