Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
236
dacorvo HF staff commited on
Commit
bc47789
•
1 Parent(s): 4ad4cf5

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/llama/abacusai/Smaug-72B-v0.1/0d8e57049c33c5b5c6d9.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3717,3 +3717,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_cae5f61e367938457a18+2c2d707e/model.neff fi
3717
  neuronxcc-2.14.227.0+2d4f85be/MODULE_cb6145854d51552ad2ae+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3718
  neuronxcc-2.14.227.0+2d4f85be/MODULE_df8fba2abca3d0417a12+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3719
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7bd7a2134c7496f5ce9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3717
  neuronxcc-2.14.227.0+2d4f85be/MODULE_cb6145854d51552ad2ae+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3718
  neuronxcc-2.14.227.0+2d4f85be/MODULE_df8fba2abca3d0417a12+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3719
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7bd7a2134c7496f5ce9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3720
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3721
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/abacusai/Smaug-72B-v0.1/0d8e57049c33c5b5c6d9.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": true, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 24576, "max_position_embeddings": 32768, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "abacusai/Smaug-72B-v0.1", "checkpoint_revision": "a1d657156f82c24b670158406378648233487011", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 64, "pad_token_id": 151643, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "seq_length": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 152064}
neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4773acc47b12ee9fd271097e816068bdcc7b5d34249c69a001533430bfadf966
3
+ size 847637
neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1861560dd2f59da12dd0fa61958b506532b7407fac4a5b465e66fefb862f62
3
+ size 12258304
neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe416a1126e6e3b943574327631360033b8904c6781e339ce23f15972d97547
3
+ size 1086022
neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8888da4c912ccf80eea1a18c788cb71ff6ec00a1e0b484ee19dad40809bfa589
3
+ size 7783424