Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
34d2e6b
·
verified ·
1 Parent(s): 2b97fa3

Synchronizing local compiler cache.

Browse files
Files changed (15) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/HuggingFaceH4/zephyr-7b-beta/b4ba7de14335ba8730a5.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_583cb20693015ec36ef1+613edded/model.hlo_module.pb.lock +0 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/compile_flags.json +1 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.done +0 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.hlo_module.pb +3 -0
  11. neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.neff +3 -0
  12. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/compile_flags.json +1 -0
  13. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.done +0 -0
  14. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.hlo_module.pb +3 -0
  15. neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7171,3 +7171,6 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_68ab7b1f3ada0d3e4f41+613edded/model.neff fi
7171
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d1581937ee5c6df81b5c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7172
  neuronxcc-2.16.372.0+4a9b2326/MODULE_8afc89b9c18489780471+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7173
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c27b585b0715d8fd83b8+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
7171
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d1581937ee5c6df81b5c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7172
  neuronxcc-2.16.372.0+4a9b2326/MODULE_8afc89b9c18489780471+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7173
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c27b585b0715d8fd83b8+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7174
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7175
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7176
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/HuggingFaceH4/zephyr-7b-beta/b4ba7de14335ba8730a5.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": 16, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+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_3b9cc972c9e78ef8a619+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91fcd64c294b47473aff454ea3745f2c80e0f1a1f0e95fcb0fd8b48c001c099
3
+ size 363413
neuronxcc-2.16.372.0+4a9b2326/MODULE_3b9cc972c9e78ef8a619+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb3536901789996d8564ef6e01c7880fdef7cbbb88e7bcf27e938ae294ebe6c
3
+ size 3001344
neuronxcc-2.16.372.0+4a9b2326/MODULE_583cb20693015ec36ef1+613edded/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+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_5f194d47737258040d3c+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a918b2cfaaa18d2029b6bfb05bd04b5d046bc649bc6a9f1dd10323a1091fb1
3
+ size 363413
neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8a82317725a5f18a1fbe4a2de5a7987d404706f6d329829841989ab1e165a6
3
+ size 3574784
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+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_6c97395a3fefb42ecdbc+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc286fb1eddba957e11b26089a43155d2960cdbeb42e24031ac496715f83f662
3
+ size 537196596
neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81eef68c755302ef9570675a42e7483877b2d03461fc53fe02a4b6d4f8f897e6
3
+ size 28017664