Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
454
dacorvo HF Staff commited on
Commit
fd4c197
·
verified ·
1 Parent(s): 45611c1

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/Qwen2.5-72B-Instruct/c5c1741f99946dfc740e.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7283,3 +7283,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.neff fi
7283
  neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7284
  neuronxcc-2.16.372.0+4a9b2326/MODULE_0acad42a944795753dda+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7285
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b41edc3f83cd80184989+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7283
  neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7284
  neuronxcc-2.16.372.0+4a9b2326/MODULE_0acad42a944795753dda+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7285
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b41edc3f83cd80184989+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7286
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+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
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/c5c1741f99946dfc740e.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": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "495f39366efef23836d0cfae4fbe635880d2be31", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "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_6839e55c8e5b5c51afc8+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_6839e55c8e5b5c51afc8+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c7a404760db449f77c40dcff65c4fa90ce606edafcfea9f9d7125ea7133eb8
3
+ size 1225121
neuronxcc-2.16.372.0+4a9b2326/MODULE_6839e55c8e5b5c51afc8+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703d008d6cbf057de01762cf4978fc96b1650dd3530b90f8cf52c29c3aa10959
3
+ size 2581504
neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+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_a4f284cbde01093ed6be+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d50a155b723fb1b4bae3ad95635812c3a0a392bd5af9254fdae36381755969b
3
+ size 1023825
neuronxcc-2.16.372.0+4a9b2326/MODULE_a4f284cbde01093ed6be+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846f909bcf4fb5ba0cb661f0dcb15bd6f1e8bcd7860b5c1d407ca00bbdc44fc2
3
+ size 9432064