Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
203
dacorvo HF staff commited on
Commit
292f981
•
1 Parent(s): 711b800

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Llama-2-13b-chat-hf/03b6c7125f076563bd68.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2182,3 +2182,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_da61ba5a3e15c764428a+2c2d707e/model.neff fi
2182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc5d572670bf11c06b07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2183
  neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2184
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc5d572670bf11c06b07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2183
  neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2184
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2185
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2186
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Llama-2-13b-chat-hf/03b6c7125f076563bd68.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": 32, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "29655417e51232f4f2b9b5d3e1418e5a9b04e80e", "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_1547861732b1c5b47a02+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ba42e3b009eb7cf54e206d0acb73eca9d22ef90b6284b3454fbb0d4569438c
3
+ size 478026
neuronxcc-2.13.66.0+6dfecc895/MODULE_1547861732b1c5b47a02+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361069221859db22965915f92781eae688eff6afcd6f4e292190964d531c47e9
3
+ size 23317504
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea1cf53bac85d2c232e67a1b67b2f996bb150db538c518b0bb2a74a136f5338
3
+ size 422008
neuronxcc-2.13.66.0+6dfecc895/MODULE_3f0a486040417ad7e32f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5980dd5c9d2aef8354f1b27bab36ee361a6a828a69c953166196fa54298e04f0
3
+ size 5827584