Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
243
dacorvo HF staff commited on
Commit
0aeb7b9
•
1 Parent(s): a62a55a

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/d1773b7cfd9ce7a916e6.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2869,3 +2869,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_854110d865212cc7631d+2c2d707e/model.neff fi
2869
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ad05b76669ff1319a131+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2870
  neuronxcc-2.13.66.0+6dfecc895/MODULE_bc55534a8a895d27c96b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2871
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dd73cf6430018dbf30ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2869
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ad05b76669ff1319a131+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2870
  neuronxcc-2.13.66.0+6dfecc895/MODULE_bc55534a8a895d27c96b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2871
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dd73cf6430018dbf30ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2872
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2873
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+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/d1773b7cfd9ce7a916e6.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": 4, "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": 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_62af34a8b34ede5ed98d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8ef7b688d31c9ddf4e2e1ed4d65fe2e8d90e154f7aca0e996f7a3edfbb2dd4
3
+ size 343832
neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad2da3fd13973e6cd93e8ee7d9c2988a944d03437ea21cead0bf130d7b77ed9
3
+ size 14470144
neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9202ad2e9258377560b4838d778429a79cdd3c83e7f8ab3afd1469c59ecd45c
3
+ size 397220
neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89a0d81c8bf090518efdd3c0d3c194bfadbb9bf79d94d41ca9a91863127200f
3
+ size 12329984