Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
204
dacorvo HF staff commited on
Commit
590e7d5
•
1 Parent(s): 45bce57

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/1f1367c0cc366a15a9ed.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3529,3 +3529,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_1b5c818736672b0caa4f+2c2d707e/model.neff fi
3529
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d37f7b6ed8d8507b7fd8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3530
  neuronxcc-2.14.227.0+2d4f85be/MODULE_1e957b55451b33f9baf4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3531
  neuronxcc-2.14.227.0+2d4f85be/MODULE_53e5d3e778bea8290295+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3529
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d37f7b6ed8d8507b7fd8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3530
  neuronxcc-2.14.227.0+2d4f85be/MODULE_1e957b55451b33f9baf4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3531
  neuronxcc-2.14.227.0+2d4f85be/MODULE_53e5d3e778bea8290295+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3532
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3533
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+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/1f1367c0cc366a15a9ed.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": 16, "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_84e79569f870b8449513+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875ee3c4ce31c6a9834a90190a304d53a8b23b1b5e4f002fef2c246834637170
3
+ size 422165
neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d87d543fa62c1d0e9d7887a35ff8dc4aa54229d1d7865b80bb923233eb46224
3
+ size 6298624
neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30cf1251c530e49cece2b809e1d2b9c91ed1c1c02872b36431b9852455adb5c
3
+ size 543422
neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d78f9242a2391d4b668221b541db14ae74a4a95ca9bd22c9998d8faaa8bba4
3
+ size 29901824