Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
b85eb9c
·
verified ·
1 Parent(s): edd53e8

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/Qwen2.5-1.5B/6969c5fcdac32e8a7f54.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7279,3 +7279,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.neff fi
7279
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7280
  neuronxcc-2.16.372.0+4a9b2326/MODULE_8c471c6177f9ccf5161f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7281
  neuronxcc-2.16.372.0+4a9b2326/MODULE_af851f29f02d40b1c4fb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7279
  neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7280
  neuronxcc-2.16.372.0+4a9b2326/MODULE_8c471c6177f9ccf5161f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7281
  neuronxcc-2.16.372.0+4a9b2326/MODULE_af851f29f02d40b1c4fb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7282
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+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
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-1.5B/6969c5fcdac32e8a7f54.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": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-1.5B", "checkpoint_revision": "8faed761d45a263340a0528343f099c05c9a4323", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+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_26cfa6f50e115413cd0f+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22111ea3e0e61a4027868fd2982807af2020225a0304e4f26bda36433c97a71
3
+ size 427437
neuronxcc-2.16.372.0+4a9b2326/MODULE_26cfa6f50e115413cd0f+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b70128d8893f43ad081ebed0e9db8a6f05711d534bb46240cfcce71a08a309
3
+ size 27403264
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+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_e2756d5b6b00a585f565+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84c494b62500374a7bfbe3878326d9c3ade4ad83568529822bfa1b865fbe7f7
3
+ size 354884
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2756d5b6b00a585f565+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96262d5074c0f0e2f2443b5f48def2f32121fe354dad5ebd2e8751501ba5dc12
3
+ size 2786304