Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
408
dacorvo HF Staff commited on
Commit
4265727
·
verified ·
1 Parent(s): fcd338b

Synchronizing local compiler cache.

Browse files
Files changed (12) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/meta-llama/Meta-Llama-3.1-8B/1e202b999f7f54120fb6.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff +1 -1
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff +1 -1
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/compile_flags.json +1 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.done +0 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.hlo_module.pb +3 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff +3 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/compile_flags.json +1 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.done +0 -0
  11. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.hlo_module.pb +3 -0
  12. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7091,3 +7091,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_bb75bd958aecae2328f2+613edded/model.neff fi
7091
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c0edba1973e95b5f18d0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7092
  neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1b42c1b8d27e328577+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7093
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f6243540544ea23fcfe1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7091
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c0edba1973e95b5f18d0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7092
  neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1b42c1b8d27e328577+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7093
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f6243540544ea23fcfe1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7094
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7095
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/meta-llama/Meta-Llama-3.1-8B/1e202b999f7f54120fb6.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": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 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-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55254fa7cc84ed2c53d21177d4593a3d67aee29ac21b8ea690b080b327d622d6
3
  size 7803904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ebf416056af21adc3bc3d71057c68e6353e2f8d7e384b6741366543b8ec0de
3
  size 7803904
neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ee9cc60f35b7a6d07a396cdb7952d261dfb276e4bf4bab8c5ad41e7ad16b995
3
  size 5970944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7c98cc9bf2a57760705a932a6f1c62de9f0d31c125e997d8b03d2ae2ad602a
3
  size 5970944
neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+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_7c7f9bc845414ce6b5a4+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753c7e991c37fd758fce35ec518e6c4110078338e1944860abb044833be86be6
3
+ size 446610
neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dc2a42eb970f65a692123d929236a469a216ceede8b2129df0cd2ccaca26e7
3
+ size 6042624
neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+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_fac5455884c9dfdee723+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/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-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9745b0e63860d8d1c07a88c52d0361b4e9f86c89dd586d94d7a6afd3decfb6d0
3
+ size 10415104