Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
1e5b557
·
verified ·
1 Parent(s): 597374c

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.dev1/inference/phi3/microsoft/phi-4/aefe5e89e89e5ba40a59.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7458,3 +7458,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_eca56defe775a7981c4b+613edded/model.neff fi
7458
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f6b2b8267d631f2f0fad+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7459
  neuronxcc-2.16.372.0+4a9b2326/MODULE_767b99765e404104c7bb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7460
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f65495564d03f1c90e3a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7458
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f6b2b8267d631f2f0fad+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7459
  neuronxcc-2.16.372.0+4a9b2326/MODULE_767b99765e404104c7bb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7460
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f65495564d03f1c90e3a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7461
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7462
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/phi3/microsoft/phi-4/aefe5e89e89e5ba40a59.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": 24, "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_51c384f52e045bea30bd+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_51c384f52e045bea30bd+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcec7982ab6e09bb4a4be970b48046bcbea19fb353eceacee54c5e67b8085907
3
+ size 454072
neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3436d0245317eb88fad4a88292ccc454d4606597e2950ccb8bcf8adf8a546bf3
3
+ size 6329344
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+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_6c9037784aa88d983971+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbde16bb6ae19565b03b2a9042524a9ce856c39970bb86c64b8951131be83cf
3
+ size 557419
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ced297d1f9dbb0f2b9456efed3159c2a1174aee5ee59ccaa57836def8079330e
3
+ size 2571264