Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
272
dacorvo HF staff commited on
Commit
e6331d6
•
1 Parent(s): 7f7ce1f

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/b5948eec4de2ae70689e.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2771,3 +2771,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_08a92bdfda6dd6a871c4+2c2d707e/model.neff fi
2771
  neuronxcc-2.13.66.0+6dfecc895/MODULE_56df7341992781ddecbf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2772
  neuronxcc-2.13.66.0+6dfecc895/MODULE_5b3838730ba99c5c4884+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2773
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b907011671cb6f74399f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2771
  neuronxcc-2.13.66.0+6dfecc895/MODULE_56df7341992781ddecbf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2772
  neuronxcc-2.13.66.0+6dfecc895/MODULE_5b3838730ba99c5c4884+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2773
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b907011671cb6f74399f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2774
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2775
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+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/b5948eec4de2ae70689e.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": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "abf8f1bbc9f1ceefa4e88667311436858dd75de0", "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_1c885e579db96c4968ec+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3dfba9d2c79a927913bff38b175acd4bbc8a87cb9d6969970d40a663de0c6a7
3
+ size 397595
neuronxcc-2.13.66.0+6dfecc895/MODULE_1c885e579db96c4968ec+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d154996ad288ffee541c0139048fed5e0c35fe8ab6dad5e757860f04b15e211
3
+ size 6247424
neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d225817d6368586cbe956bb4f69d7c49e1780a0c35ac6010c7a7c9b498e99887
3
+ size 344207
neuronxcc-2.13.66.0+6dfecc895/MODULE_dd7136b470e5ecb07975+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7976b3a23a2f6174d007da67f403951cd0e7e5b39717f888ac5817e19895bd
3
+ size 30147584