Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
696
dacorvo HF Staff commited on
Commit
7172d07
·
verified ·
1 Parent(s): 5117e6a

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-14B/3df3c00b7d3582dbbade.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7287,3 +7287,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.neff fi
7287
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7288
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cae7c5043181d0d1e84d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7289
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d96d38302f6e06310c28+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7287
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7288
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cae7c5043181d0d1e84d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7289
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d96d38302f6e06310c28+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7290
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7291
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-14B/3df3c00b7d3582dbbade.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 131072, "max_window_layers": 48, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-14B", "checkpoint_revision": "97e1e76335b7017d8f67c08a19d103c0504298c9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 48, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_scaling": null, "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-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+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_3a6d5511f840a5d2088a+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e5881a8797e5ae91b6c5016765ef8bed85268d3259e1213bd4d6ddfd9ba47d
3
+ size 663927
neuronxcc-2.16.372.0+4a9b2326/MODULE_3a6d5511f840a5d2088a+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1233e7829123c3d1e18678ea284a0d52834bf3c3779f219bad92ae48b602bb57
3
+ size 2765824
neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+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_eb1ba6256bb5b7f6ee83+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93264ea67de142ca936abe6f6bd361b1c9fb97ee4b045e80dfeaf30c8cae73f
3
+ size 560492
neuronxcc-2.16.372.0+4a9b2326/MODULE_eb1ba6256bb5b7f6ee83+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57a092d3dbbcbbc1371f513c25271984dd77a125c97d76f4798ec6b646aa3d2
3
+ size 4701184