Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
202
dacorvo HF staff commited on
Commit
6e54dde
•
1 Parent(s): ef15747

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/6b851dcb4093a8a0aa2c.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3523,3 +3523,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_ac8afff433a57ca52c2e+2c2d707e/model.neff fi
3523
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1c494dd9aa2257122db+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3524
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3525
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3523
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1c494dd9aa2257122db+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3524
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6764223987f890ad651b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3525
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f15775e63bba0c1e6815+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3526
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3527
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/6b851dcb4093a8a0aa2c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92aac29e1eb4186bcd97b8bf389ee21feec31612f1a0dd38969364b91808db3c
3
+ size 542462
neuronxcc-2.14.227.0+2d4f85be/MODULE_563d409c774fab7985d8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91899daf034c21f33b212f3a93715b86a802b580c13500d51e3f0ec3752fd08f
3
+ size 5377024
neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db96e57d4a74a08680507f6a37acd01897f708b322b2d4881470feb966f0d4
3
+ size 421205
neuronxcc-2.14.227.0+2d4f85be/MODULE_cf49d142fac0a0b3b4d2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5186c30f85826697f3f683593772edde2c2e630b38e634a05f7ac64dea34c6a4
3
+ size 7025664