Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
41acb18
·
verified ·
1 Parent(s): 86f51f0

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/Qwen2.5-7B-Instruct/f5439bbe2f98d94faef3.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7234,3 +7234,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_39cb90b37ee6fff24f5d+613edded/model.neff fi
7234
  neuronxcc-2.16.372.0+4a9b2326/MODULE_45dec79bcb55d7eacd60+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7235
  neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7236
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7234
  neuronxcc-2.16.372.0+4a9b2326/MODULE_45dec79bcb55d7eacd60+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7235
  neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7236
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7237
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7238
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+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/Qwen2.5-7B-Instruct/f5439bbe2f98d94faef3.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": "a09a35458c702b33eeacc393d103063234e8bc28", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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_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_2694a26b0ce70a599f06+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_2694a26b0ce70a599f06+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27cb4056e69d06b5d73f286564a65ee74e43791e2166516d4af97d312e7dd45e
3
+ size 355332
neuronxcc-2.16.372.0+4a9b2326/MODULE_2694a26b0ce70a599f06+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c5c1a10ebfc08d0927263ea9fae2be8f5ce8368362679c0b73e11a06ce5188
3
+ size 9913344
neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+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_897754cf13afc8dd55a7+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746e69389ffd3a2d54ec2e89700a1990c1436303d4e73338729153c01cf0d9ad
3
+ size 428109
neuronxcc-2.16.372.0+4a9b2326/MODULE_897754cf13afc8dd55a7+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa444e1fad75a893cc233e8555558b09c7c645dbc050ebb1cc86f3ee3be1ddf
3
+ size 6892544