Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
243
dacorvo HF staff commited on
Commit
136eae1
•
1 Parent(s): 241945e

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/73f443c93793ac2a0176.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2652,3 +2652,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_d5e5e35c4b9105b69867+2c2d707e/model.neff fi
2652
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e9f964a925c5418d1e93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2653
  neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2654
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2652
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e9f964a925c5418d1e93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2653
  neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2654
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2655
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2656
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+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/73f443c93793ac2a0176.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": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "abf8f1bbc9f1ceefa4e88667311436858dd75de0", "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/MODULE_b54a08c18ad776940cd0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12b7e0f0196d4882d7fa47c82821f6c3f208713d87be0b9c5effec8da2f07ddd
3
+ size 397220
neuronxcc-2.13.66.0+6dfecc895/MODULE_b54a08c18ad776940cd0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de3bc2fcab6b09fa620c2b75d64ab29022151348b76b4015f228cf740b28617
3
+ size 13876224
neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ec8b934f5a3c38f4569d1cadbcc3cc188aa91b996bfb53bb73a9734f57c7d6
3
+ size 343832
neuronxcc-2.13.66.0+6dfecc895/MODULE_b59ff3b7e545f85152c8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6965e159d8e2b8ab18927b3d83f2c38335a9b4307c30de8c13f0d8115d45dd9
3
+ size 14449664