Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
c10d209
•
1 Parent(s): 8781979

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/b7560956533191c18ac8.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2362,3 +2362,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff fi
2362
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2363
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2364
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2362
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2363
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2364
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2365
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+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
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/b7560956533191c18ac8.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": 2, "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_4d9f16f5c3f401d9802e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fff66daa9d0129a30661ea1425b739621b6006a74f2277b8033bc88911d85b
3
+ size 345623
neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dabd11b2e509ab756fb86e728488c4a4ff776f639d51652062f0b58e46c61eb
3
+ size 13190144
neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c291bdc335f35af994e9e9dc7fa814c24e42c9725ff2efb9f48a976074eaace0
3
+ size 398979
neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044e4876b0b5b412b31ab3aff83ec94699f0afa7cbcabb6ad971d042e93d7aec
3
+ size 13999104