Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
443
dacorvo HF Staff commited on
Commit
c1a127d
·
verified ·
1 Parent(s): c5b948d

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/7cb785902a13105eed58.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7228,3 +7228,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/text_encoder/model.neu
7228
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
7229
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
7230
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 
 
 
7228
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
7229
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
7230
  neuronxcc-2.16.372.0+4a9b2326/MODULE_54ad43f123eecd242b32/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
7231
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7232
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+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/7cb785902a13105eed58.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": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+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_5d5e4206a466b7852561+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/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-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28cb7ab694c8773c748b0a8e510b81fbad65ac7d3e1eafc39308d2519446f8af
3
+ size 9554944
neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+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_b5092ae1e071cef3fe8a+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e53f2358531c7792459225c5a93d7f26628125c70fe18150527da859a6faebb
3
+ size 428109
neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65691e4da08866ec16acfd84f65756fd050a77e05534b5e90b59fd372b2491f5
3
+ size 6892544