Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
ef15747
•
1 Parent(s): 70b5e61

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/d45199ec3e6e802b71c2.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3521,3 +3521,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_f100b7f5a1c01815ffb6+2c2d707e/model.neff fi
3521
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fcd85d066cb013a59267+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3522
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ac8afff433a57ca52c2e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3523
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1c494dd9aa2257122db+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3521
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fcd85d066cb013a59267+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3522
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ac8afff433a57ca52c2e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3523
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1c494dd9aa2257122db+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3524
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3525
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/d45199ec3e6e802b71c2.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6c9b63d373e5a6f8e09ee63b91ba81b9d3f015e74b27a4a6eae4bd07207c0e
3
+ size 543422
neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a516decb06107ec2af1a27b1d1e0c766b8faf57200eb330dfa1915caa940792
3
+ size 29901824
neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd06ff3a70cbd1ea813d56f0b8f793270e48cb62cc36e6ca3ff1b39e6fb46d9c
3
+ size 422165
neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a214a3a7cfd78a6b7f34b121ded62f6b5a5582789f682deca30d2705f7b757
3
+ size 3800064