Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
dacorvo HF staff commited on
Commit
b2511a0
•
1 Parent(s): d691d8f

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/Llama-2-13b-chat-hf/3aadd8af5d064e1d796a.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2855,3 +2855,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_2b7f965b97b6ad78213e+2c2d707e/model.neff fi
2855
  neuronxcc-2.13.66.0+6dfecc895/MODULE_bb7dc7c3210ea0babefd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2856
  neuronxcc-2.13.66.0+6dfecc895/MODULE_3058b4654408499cae1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2857
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4cfa2f6bce43302cd721+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2855
  neuronxcc-2.13.66.0+6dfecc895/MODULE_bb7dc7c3210ea0babefd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2856
  neuronxcc-2.13.66.0+6dfecc895/MODULE_3058b4654408499cae1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2857
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4cfa2f6bce43302cd721+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2858
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2859
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+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/Llama-2-13b-chat-hf/3aadd8af5d064e1d796a.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 12, "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-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c26e85ccf481d6ae99d96d12906532462d3a4abc76e6c78044be92904c32dc
3
+ size 475811
neuronxcc-2.13.66.0+6dfecc895/MODULE_b40601af558a2e5525b2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65012ff1e481d32fcbd88df446858281cb0845040b3982e796f63b044588d390
3
+ size 7947264
neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a6c81e8aff388e8e289b6ac7cea13525103c49933f5ce92f8822afc26b2a1a
3
+ size 419753
neuronxcc-2.13.66.0+6dfecc895/MODULE_d565355fcd22aa83e4ba+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28818ec5038bcc250f67303edd9c702d184cde8482287c846834335554604bc
3
+ size 6493184