Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
630
dacorvo HF Staff commited on
Commit
f9539dd
·
verified ·
1 Parent(s): 6f70182

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev2/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/1b2e67b756cb8b826362.json +1 -0
  3. neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/compile_flags.json +1 -0
  4. neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.done +0 -0
  5. neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.hlo_module.pb +3 -0
  6. neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.neff +3 -0
  7. neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/compile_flags.json +1 -0
  8. neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.done +0 -0
  9. neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.hlo_module.pb +3 -0
  10. neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -6948,3 +6948,5 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_cab1c4eb6533d0e53c54+39f12043/model.neff fi
6948
  neuronxcc-2.15.143.0+e39249ad/MODULE_cc5981296dce23fea50a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6949
  neuronxcc-2.15.143.0+e39249ad/MODULE_1cb44cb62d1004e20759+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6950
  neuronxcc-2.15.143.0+e39249ad/MODULE_cb3ceed5baf6cff96237+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
6948
  neuronxcc-2.15.143.0+e39249ad/MODULE_cc5981296dce23fea50a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6949
  neuronxcc-2.15.143.0+e39249ad/MODULE_1cb44cb62d1004e20759+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6950
  neuronxcc-2.15.143.0+e39249ad/MODULE_cb3ceed5baf6cff96237+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6951
+ neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
6952
+ neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev2/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/1b2e67b756cb8b826362.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": 4, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "a09a35458c702b33eeacc393d103063234e8bc28", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4f66c60bbc504ba8cebeb09db3c541de4a63cdbf3b63abc665da6d73d99c41
3
+ size 355332
neuronxcc-2.15.143.0+e39249ad/MODULE_5d5e4206a466b7852561+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99debade553977c16b0af2b671d71703979f926a1169d7071fe0087480122b1
3
+ size 10865664
neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4259edb17df1f7e6e031b5e77c161e3293d02c2c4d901481e893d41a66dd41
3
+ size 426429
neuronxcc-2.15.143.0+e39249ad/MODULE_f382de6faf84786b110f+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c895ebc291ba71b818a26e31c29fd65f50725f9d79abf9405467635a923c63f7
3
+ size 6544384