Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
e5d5bbe
•
1 Parent(s): bbc86ce

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Llama-2-70b-chat-hf/1c0ffc384d07e27fbe8a.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2196,3 +2196,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_cc88fcd266266515d56a+2c2d707e/model.neff fi
2196
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ea2e91b07024a4c5a6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2197
  neuronxcc-2.13.66.0+6dfecc895/MODULE_efd165bd378d3b8e92aa+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2198
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2196
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ea2e91b07024a4c5a6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2197
  neuronxcc-2.13.66.0+6dfecc895/MODULE_efd165bd378d3b8e92aa+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2198
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2199
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2200
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Llama-2-70b-chat-hf/1c0ffc384d07e27fbe8a.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": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-70b-chat-hf", "checkpoint_revision": "8b17e6f4e86be78cf54afd49ddb517d4e274c13f", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "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-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1de0439c29eb3d608eb95a6acae5e85169586049ac1512c3ae11b34546d4b4f
3
+ size 849280
neuronxcc-2.13.66.0+6dfecc895/MODULE_38ddb60b8a501e730f76+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2bd11334dbc7490519c2974e922915a46797ccfa4279d6969fdda970a2d6f1
3
+ size 6595584
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a47da716e4a8bb9da4b877b031e9f6d968e78e212014eeb6ee64ce719f8073
3
+ size 962875
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5ff5e4fa70824f365b1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050409922ed008f0bf37ec425ab8e8edaed0e9b8982871b0f7b691e458582daa
3
+ size 13528064