Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
449
dacorvo HF Staff commited on
Commit
8a5daf9
·
verified ·
1 Parent(s): 1c5284b

Synchronizing local compiler cache.

Browse files
Files changed (11) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev2/inference/llama/meta-llama/Meta-Llama-3.1-8B/203257ce417bac36e427.json +1 -0
  3. neuronxcc-2.15.143.0+e39249ad/MODULE_a89ef5a5abc47372ac48+39f12043/model.neff +1 -1
  4. neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/compile_flags.json +1 -0
  5. neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.done +0 -0
  6. neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.hlo_module.pb +3 -0
  7. neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.neff +3 -0
  8. neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/compile_flags.json +1 -0
  9. neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.done +0 -0
  10. neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.hlo_module.pb +3 -0
  11. neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -6926,3 +6926,5 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_b866400da5e53b3486cc+39f12043/model.neff fi
6926
  neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/model.neuron filter=lfs diff=lfs merge=lfs -text
6927
  neuronxcc-2.15.143.0+e39249ad/MODULE_34d371c764b2edea8dcd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6928
  neuronxcc-2.15.143.0+e39249ad/MODULE_a89ef5a5abc47372ac48+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
6926
  neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/model.neuron filter=lfs diff=lfs merge=lfs -text
6927
  neuronxcc-2.15.143.0+e39249ad/MODULE_34d371c764b2edea8dcd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6928
  neuronxcc-2.15.143.0+e39249ad/MODULE_a89ef5a5abc47372ac48+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6929
+ neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6930
+ neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev2/inference/llama/meta-llama/Meta-Llama-3.1-8B/203257ce417bac36e427.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.15.143.0+e39249ad/MODULE_a89ef5a5abc47372ac48+39f12043/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45061067d2cd47f49237cd76fd3dbbdb369f5e5353755c16a9c651a36184bdc4
3
  size 6022144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27277d70287878c1ae246cf16744aa8701ecacedf928e2a5047a09425ae457c9
3
  size 6022144
neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5008badd073205df5963478a3dbda38e54cfee532302a1354af36482254971
3
+ size 444690
neuronxcc-2.15.143.0+e39249ad/MODULE_d0c1049c1f409a3c8074+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35496ffcddef3c3a83d63963ed5db8a535a2ae3c85083ff0054dc0c1334b4d5d
3
+ size 6063104
neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7584f405d6e93babdd7991d653f4eeb9c1a7ab41436552eefd4e9d812605f46
3
+ size 363704
neuronxcc-2.15.143.0+e39249ad/MODULE_fac5455884c9dfdee723+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef183fb7618558c0a74d7d11be16eb629e931fe2565fa319226a5f875c3cdaf
3
+ size 10456064