Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
218
dacorvo HF staff commited on
Commit
b0c5659
•
1 Parent(s): dd36392

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/5018ec39102140027dfb.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1074,3 +1074,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_6ce450eeba84f8c95243+2c2d707e/model.neff fi
1074
  neuronxcc-2.12.68.0+4480452af/MODULE_983f893836a08abb88b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1075
  neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1076
  neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1074
  neuronxcc-2.12.68.0+4480452af/MODULE_983f893836a08abb88b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1075
  neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1076
  neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1077
+ neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1078
+ neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/5018ec39102140027dfb.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496"}}
neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5eb10cea9e707d16ca1f5a86e4735222f3c8750d9561063115d0d7a61ca19b1
3
+ size 493747
neuronxcc-2.12.68.0+4480452af/MODULE_80d1d70fee2a52816554+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25264f644ff0e1e324dbeed712341e33eec55f7cc9b0ae1eefc793aab76dd34
3
+ size 3492864
neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4109f96337efae598bd08efd892da3efae57893ab0a5bffcab072e076d9b23
3
+ size 437888
neuronxcc-2.12.68.0+4480452af/MODULE_e5876df0c45df2dbcf02+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7e7c4035ce4cc4686a404b1c97eb7674485b1b78db0916495d79266c5fdcc9
3
+ size 28242944