Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
595
dacorvo HF Staff commited on
Commit
41623b0
·
verified ·
1 Parent(s): c564534

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-3-mini-4k-instruct/fc781bb5c3bd12f434ea.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7603,3 +7603,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_7e2686740d19496c3c6e+613edded/model.neff fi
7603
  neuronxcc-2.16.372.0+4a9b2326/MODULE_878607c2d60970a9fc41+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7604
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cea91d96c873419351af+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
 
 
 
7603
  neuronxcc-2.16.372.0+4a9b2326/MODULE_878607c2d60970a9fc41+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7604
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cea91d96c873419351af+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
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/Phi-3-mini-4k-instruct/fc781bb5c3bd12f434ea.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32064}
neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+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_95dae70c69a000bb4eb6+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bab3ff2f6bd20f1a08356ccaa2b911732276fa8382b6647c2c8c278e29ba74
3
+ size 243212
neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f4c72303e4b41837de619896df915672d56e13c7921bd7ac865c3c1c48cf95
3
+ size 5991424
neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+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_9f4e39af4e0b35889393+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03366ab223c8e3ed4356adf00f96ea4b5f264c37c01d32f463bc5adc191b6085
3
+ size 306683
neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd53abef382d3b95ab588d93318fce358e3451d65b5148de5919afd9aa97eb83
3
+ size 6493184