Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
200
dacorvo HF staff commited on
Commit
c756e93
•
1 Parent(s): 9cd9f28

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-2-7b-chat-hf/b69aaf189ca46eafce6e.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3493,3 +3493,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.neff fi
3493
  neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3494
  neuronxcc-2.14.227.0+2d4f85be/MODULE_43ed2dbfcc617e90b3b1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3495
  neuronxcc-2.14.227.0+2d4f85be/MODULE_b60bcc4325fd51826a5e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3493
  neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3494
  neuronxcc-2.14.227.0+2d4f85be/MODULE_43ed2dbfcc617e90b3b1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3495
  neuronxcc-2.14.227.0+2d4f85be/MODULE_b60bcc4325fd51826a5e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3496
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3497
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+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-2-7b-chat-hf/b69aaf189ca46eafce6e.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "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_059241efd2c75f6b2218+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b53f4b017c2b1215653b603c2780fe710fbe7a7dd2ae34c8ba0131ea6a302e
3
+ size 433917
neuronxcc-2.14.227.0+2d4f85be/MODULE_059241efd2c75f6b2218+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf941d1c15f675746e01af3ac8a57bf0c22c24eea136c7f7d9bdf19472c8006f
3
+ size 31130624
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e280750405c9dbb524f3bc13d71d1fc5e7f6961e086aa07a5acbcd86374b6b8
3
+ size 336834
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8ee418ed4764135d748+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8678a5103f589cb1acdcbfb4ebd2b60ec8fa3753a3dd5a212d169969fe11ebd
3
+ size 13548544