Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
255
dacorvo HF staff commited on
Commit
c86d4b0
•
1 Parent(s): 5f1d559

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/0230aad0378abcb00404.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2997,3 +2997,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_e55b4e7d808bbaf9f1a9+2c2d707e/model.neff fi
2997
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea31894e874a6024428e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2998
  neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2999
  neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2997
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea31894e874a6024428e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2998
  neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2999
  neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3000
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3001
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/0230aad0378abcb00404.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": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 8192, "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_00fe98d615fb072392ce+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd01968bc67569a3561bdf1099223fb5516fb5714ed5f7466120812a39e61d3
3
+ size 304356
neuronxcc-2.13.66.0+6dfecc895/MODULE_00fe98d615fb072392ce+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6001419e0728084f193692681689a61ef0cb9f1df3844090cfb1426e32f6c111
3
+ size 14152704
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53a17bbbf8f685b9975fdde0af7d974f42e139fc3bd06266377687b58b4aeb1
3
+ size 316131
neuronxcc-2.13.66.0+6dfecc895/MODULE_05ffcb959c9e232f6071+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97600f85c3771b92b591d7c1c71e69a8e090937e899b7fdf3eb298c596b5783
3
+ size 8786944