Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
400
dacorvo HF staff commited on
Commit
dbd445c
·
verified ·
1 Parent(s): 41623b0

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/phi-4/9c0876e5186a665fa260.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7605,3 +7605,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_cea91d96c873419351af+613edded/model.neff fi
7605
  neuronxcc-2.16.372.0+4a9b2326/MODULE_da84b070ab21ed1df54f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7606
  neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7607
  neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7605
  neuronxcc-2.16.372.0+4a9b2326/MODULE_da84b070ab21ed1df54f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7606
  neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7607
  neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7608
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7609
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/phi-4/9c0876e5186a665fa260.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100265, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17920, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "microsoft/phi-4", "checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 10, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 10, "original_max_position_embeddings": 16384, "pad_token_id": 100349, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27cbd6a3e6489625a93e9a2f1bb542a546db0be0acd0ceb9b3ae85b767cf5036
3
+ size 320252
neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129c0c9792fb4f8b05bb663c62f35e3069697ed335381d49c4b2ca4eec16d5d2
3
+ size 2397184
neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937d4e3f354a5e172224bb36132c3b6dbfa1e65e3aa0b0a6c301910b7909d84d
3
+ size 414109
neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e272757ec05b134ef4e4a43ae34fc8b4e4adaf834ea0468e6e0faa14bfd6b3
3
+ size 3718144