Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
390
dacorvo HF staff commited on
Commit
18ef883
·
verified ·
1 Parent(s): ad43148

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/mistral/mistralai/Mistral-7B-Instruct-v0.3/301ae0124c94abfffe5e.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7093,3 +7093,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1b42c1b8d27e328577+613edded/model.neff fi
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
 
 
 
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
7096
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7097
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/301ae0124c94abfffe5e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 4, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+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_09807a11872a354f278f+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8acec5167cb25a86ff3c1d04b7e543cea616e288fdca2d6711ad45402bb5ac
3
+ size 302193
neuronxcc-2.16.372.0+4a9b2326/MODULE_09807a11872a354f278f+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd1a70a4fe841e5299814953b1baa21ba763ec3a44f7cd64ea517154e246cbe
3
+ size 3349504
neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+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_e6e33ba205f30f662935+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa424b64cabff3757600ca2f26d36fa1c2eb68ca6bfd2c4940a80ba4de7c0d8
3
+ size 363669
neuronxcc-2.16.372.0+4a9b2326/MODULE_e6e33ba205f30f662935+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0cca1f3a20540bf3b9102e6cbe22aba474f02dc677079e3128895cd06f54d0
3
+ size 4711424