Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
91e880b
•
1 Parent(s): 8644efd

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/16229282c5b596d00815.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2366,3 +2366,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.neff fi
2366
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2367
  neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2368
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2366
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2367
  neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2368
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2369
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+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
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/16229282c5b596d00815.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": 8, "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_41fe2cd20b7049a9664f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f72bdd398c92a6e3c1a9d33aad80914029ee91c0de2dca893077ced7702804d
3
+ size 399354
neuronxcc-2.13.66.0+6dfecc895/MODULE_41fe2cd20b7049a9664f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7bd8e6469048c0cc64e191d7017de0855c2f3c4ce4ead811b0b7d6678c6986
3
+ size 3748864
neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76ba995ebeada8c1767b95c549e3bad089f4171be5d5bb99a1267df79075edc
3
+ size 345998
neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2cff607562af9ded07+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f62862181067fab4b62fb0a106b493f6f3e23228b283a81eed607b1b4fe6b8
3
+ size 30669824