Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
a5a4aaf
·
verified ·
1 Parent(s): d53c69d

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/Qwen2.5-32B-Instruct/de78df186edbc60ca09d.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7254,3 +7254,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_27a20b72ccf982177799+613edded/model.neff fi
7254
  neuronxcc-2.16.372.0+4a9b2326/MODULE_4a4553dc6cf05a499016+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7255
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6004a9e73e9afba8da2f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7256
  neuronxcc-2.16.372.0+4a9b2326/MODULE_bcf7d640412dc3dcfabe+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
7255
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6004a9e73e9afba8da2f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7256
  neuronxcc-2.16.372.0+4a9b2326/MODULE_bcf7d640412dc3dcfabe+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7257
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7258
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+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/Qwen2.5-32B-Instruct/de78df186edbc60ca09d.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": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-32B-Instruct", "checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd", "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": 64, "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_cee387972f464be7ea89+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_cee387972f464be7ea89+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99bed1b4045709f001827fb3437dbd112506999679706bc07537f8b80a2b014
3
+ size 749196
neuronxcc-2.16.372.0+4a9b2326/MODULE_cee387972f464be7ea89+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f6f2bb3d8f2e30c7fbebbcd086110d1ee8bc69310efda61123a0975d9ccba3
3
+ size 8930304
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+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_e2e1d5c43fb79d8804b6+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701b9e9acee91e3cfc0625d19c3813212584e820eeb0a55200fcba63566061d8
3
+ size 884860
neuronxcc-2.16.372.0+4a9b2326/MODULE_e2e1d5c43fb79d8804b6+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e457b536fa4073db643609b6da0d57313a241fc8aa47d51a598c7c33d1a1147
3
+ size 3267584