Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
7b054aa
•
1 Parent(s): f5a177c

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/mistral/NousResearch/Genstruct-7B/0249427f8c74ef4f29e3.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2054,3 +2054,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_e18006d8d069baf3335c+2c2d707e/model.neff fi
2054
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e568524f50e3326159ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2055
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2899cc9ea4177479f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2056
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fae7c4b24f88fdfee3e4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2054
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e568524f50e3326159ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2055
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea2899cc9ea4177479f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2056
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fae7c4b24f88fdfee3e4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2057
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2058
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/mistral/NousResearch/Genstruct-7B/0249427f8c74ef4f29e3.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "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": "NousResearch/Genstruct-7B", "checkpoint_revision": "532dc4500e621ee725672a92a78c18a9a319179c", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "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": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": false, "vocab_size": 32001}
neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a119584e023d6345cbba48bec940f7f6f0e9a15d2d338cc6849068f20d4a7ab
3
+ size 537236624
neuronxcc-2.13.66.0+6dfecc895/MODULE_476afa8a5cdd47db9fcb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b93cb4f5d06c3ca2a5ae538a2319cc80d46810db25de63675a89aaff05805d
3
+ size 13896704
neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88fe5bd825bcd5a8d40407bd8a7872095db1acb6b41b881df28086a879d112e3
3
+ size 399032
neuronxcc-2.13.66.0+6dfecc895/MODULE_6079eed8d405ad7216a4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875e3c2c64fa0c26b704111f0553e79e20650b9fb5db2344fe812dae8076a9b0
3
+ size 10589184