Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
276
dacorvo HF staff commited on
Commit
52e0782
•
1 Parent(s): 06eebf8

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2bdd504102100c9d1a90.json +1 -0
  3. neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/compile_flags.json +1 -0
  4. neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.done +0 -0
  5. neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.hlo_module.pb +3 -0
  6. neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.neff +3 -0
  7. neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/compile_flags.json +1 -0
  8. neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.done +0 -0
  9. neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.hlo_module.pb +3 -0
  10. neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -6386,3 +6386,5 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_ea50fe5995d21d3d8a19+39f12043/model.neff fi
6386
  neuronxcc-2.15.143.0+e39249ad/MODULE_f3be297c3485132cc12f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6387
  neuronxcc-2.15.143.0+e39249ad/MODULE_c8f106c70a445e128e0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6388
  neuronxcc-2.15.143.0+e39249ad/MODULE_fe705993427e4cf84ece+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
6386
  neuronxcc-2.15.143.0+e39249ad/MODULE_f3be297c3485132cc12f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6387
  neuronxcc-2.15.143.0+e39249ad/MODULE_c8f106c70a445e128e0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6388
  neuronxcc-2.15.143.0+e39249ad/MODULE_fe705993427e4cf84ece+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6389
+ neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6390
+ neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2bdd504102100c9d1a90.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c048cb993760c511b2e8bbada773f89b701153a0274e8f8afcb561986b3219c
3
+ size 355320
neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ee4166059fdfc6d1754eb10a947c6313cb8b61d24fe43fce2136edbc5ebc20
3
+ size 11295744
neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea75aadfbc051c05a322f02e2e8ab2be38edfa7420e312857aaefe0cad68c6c
3
+ size 426417
neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661b30935f950e9a7a7fc6fef06fb79d76925ae72ac401113425ec435d0e8873
3
+ size 6544384