Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
c2dbd15
·
verified ·
1 Parent(s): 450b26c

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/6ef36cb4ba2e070c3851.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7250,3 +7250,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_b9590ed9c31d4df0c51e+613edded/model.neff fi
7250
  neuronxcc-2.16.372.0+4a9b2326/MODULE_ee5a49c56a344198cfa3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7251
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a43b49c96d7e4fd61861+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7252
  neuronxcc-2.16.372.0+4a9b2326/MODULE_dacf103d71acbb807bc3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7250
  neuronxcc-2.16.372.0+4a9b2326/MODULE_ee5a49c56a344198cfa3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7251
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a43b49c96d7e4fd61861+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7252
  neuronxcc-2.16.372.0+4a9b2326/MODULE_dacf103d71acbb807bc3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7253
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7254
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+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/6ef36cb4ba2e070c3851.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": 1, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "a09a35458c702b33eeacc393d103063234e8bc28", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "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_27a20b72ccf982177799+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_27a20b72ccf982177799+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae901dba502c5199888d0a5d7d16229c02b0bd9f65a6640c349d08d4a9585c6c
3
+ size 387764
neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9367dac11824e9260b6270e3dd3bd9bed78c936a5316261f99b3ac31bb45962
3
+ size 28785664
neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+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_4a4553dc6cf05a499016+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68242e316b302db9856f600a8784a643ef600223d95cf374e45dabda7e5b9cb
3
+ size 327365
neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aaef0bb68a01e293fb5ea8f5686af521c492557a4e32052e567586d0440a43c
3
+ size 2315264