Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
dacorvo HF staff commited on
Commit
bd5553f
•
1 Parent(s): 2d07081

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/453556a9ea464d9e3451.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2887,3 +2887,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_7bcd4d351c30a9eaaba2+2c2d707e/model.neff fi
2887
  neuronxcc-2.13.66.0+6dfecc895/MODULE_7e8c1eeb107b2de53d8c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2888
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b2a35d6123b088d8cd44+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2889
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d45bc57dbca7a80c1988+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2887
  neuronxcc-2.13.66.0+6dfecc895/MODULE_7e8c1eeb107b2de53d8c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2888
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b2a35d6123b088d8cd44+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2889
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d45bc57dbca7a80c1988+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2890
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2891
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+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/453556a9ea464d9e3451.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": "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_250923e7da70f227865e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04ddcc10c1c28376874f628a2467d12ca4aa1912ffa4f432eb105d8cd8bafa4
3
+ size 419753
neuronxcc-2.13.66.0+6dfecc895/MODULE_250923e7da70f227865e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46a7229b1048b89fbaa3c4b6f1de947d7a4ebbc41a5008c56bedc3c88545fbe
3
+ size 6482944
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7d35d144012d0986faef9310161fc7b819b9919858aa076ccb900011227b64
3
+ size 475811
neuronxcc-2.13.66.0+6dfecc895/MODULE_2d6a0c3f060f3fd3f6e2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f6b8291cfbe3b857fbeb05702c67ebf18746daf7bf9f32586292e90bbb9d27
3
+ size 23757824