Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
252
dacorvo HF staff commited on
Commit
89f5ca4
•
1 Parent(s): cd7745b

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/Meta-Llama-3-8B/34dde08b0097894b5d53.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3535,3 +3535,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_53340fb9d4a801aa9442+2c2d707e/model.neff fi
3535
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5a7d974580d76a363137+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3536
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3537
  neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3535
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5a7d974580d76a363137+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3536
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3537
  neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3538
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3539
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+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/Meta-Llama-3-8B/34dde08b0097894b5d53.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 48, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "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-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285a111fab8c7c5f67928554eee2b6fd79bd84f276f9e46642ed3ae1778e1b03
3
+ size 361605
neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed123012f2ccc0c1ab4fa2e62d83e5dc49015f01e111d0c99ad06a88b9803b7
3
+ size 6820864
neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bf105b6424d865c473124f3a97e23cb11e0178568c0cb38e844e35cd26623a
3
+ size 446781
neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f360b46b805a5cc6cea8c8163d0570bea37bfe50aefa087be359a096f2ca9824
3
+ size 19088384