Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
276
dacorvo HF staff commited on
Commit
95ad50a
•
1 Parent(s): 753b16f

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/1e65e839a8e8340de053.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3763,3 +3763,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.neff fi
3763
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3764
  neuronxcc-2.14.227.0+2d4f85be/MODULE_40e7656f7a5181e049e4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3765
  neuronxcc-2.14.227.0+2d4f85be/MODULE_64cfa95f825f033f2cf4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3763
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3764
  neuronxcc-2.14.227.0+2d4f85be/MODULE_40e7656f7a5181e049e4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3765
  neuronxcc-2.14.227.0+2d4f85be/MODULE_64cfa95f825f033f2cf4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3766
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3767
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/1e65e839a8e8340de053.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": 16, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "b70e0c9a2d9e14bd1e812d3c398e5f313e93b473", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5bad198bc0daad1a6f5f44296f82c05d18280cdcfa2cfab657ee224b3bc1d0
3
+ size 360349
neuronxcc-2.14.227.0+2d4f85be/MODULE_0ca7c73b786eb5f0561d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcf2eeee5f84a096b6c59c4f6e9b92a56e95c6bf0afa98cffbcdf96b8b1952b
3
+ size 3871744
neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88e9b169fd008ecad87998583af7faa0702b552de036e008f858e3c6a1d9325
3
+ size 537201564
neuronxcc-2.14.227.0+2d4f85be/MODULE_c2e410de544655692966+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7887f516faae7a50e9266751e1c5799f2330358636a7c70f1aeae73d69231c5e
3
+ size 32902144