Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
5bb937c
•
1 Parent(s): ed8cde3

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/Meta-Llama-3-8B/8d5fbc3ac6577d1635b4.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2370,3 +2370,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/model.neff fi
2370
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2371
  neuronxcc-2.13.66.0+6dfecc895/MODULE_524db87565f07a8d745a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2372
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a944e823f5c7a565bbfc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2370
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2371
  neuronxcc-2.13.66.0+6dfecc895/MODULE_524db87565f07a8d745a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2372
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a944e823f5c7a565bbfc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2373
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2374
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+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/Meta-Llama-3-8B/8d5fbc3ac6577d1635b4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "561487d18c41c76bcb5fc6cfb73a324982f04f47", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ca2e582618b605e58f9a9a03064ad40f3467b8216efd2f01e7b2657a297ee4
3
+ size 399354
neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5f85641dfd1a93c6abb50ff6e16e66604c3d47fff34ede2022febb1108b2ed
3
+ size 5868544
neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91f99066553a2d2757ac06c5a3a6dbc6dc44f9ae8b675821f266b97428e88ed
3
+ size 345998
neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08515bc90ba38af5acf0fa8d8fc8289d6150027d2464d18141ee4971ad2307d6
3
+ size 30669824