Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
239
dacorvo HF staff commited on
Commit
7be4a16
•
1 Parent(s): 11bcb22

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/Meta-Llama-3-70B/e39e90cc13673d8abe1d.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2372,3 +2372,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_524db87565f07a8d745a+2c2d707e/model.neff fi
2372
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a944e823f5c7a565bbfc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2373
  neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2374
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2372
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a944e823f5c7a565bbfc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2373
  neuronxcc-2.13.66.0+6dfecc895/MODULE_24b374d43be11ae153c9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2374
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ed08451c8d838fd56480+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2375
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2376
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+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/Meta-Llama-3-70B/e39e90cc13673d8abe1d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-70B", "checkpoint_revision": "a897071033c208db3c2fdba8a1f4b1b3e2fbb283", "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": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff1c326a5af628b187686ca0afec042268f1972e631510efd29c3d589fd58da
3
+ size 962875
neuronxcc-2.13.66.0+6dfecc895/MODULE_00c44e05161052cccaa0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b988b2595b69b378415ed32ba395e961da5bdc37092909e2cb59a58218a9ac6
3
+ size 13569024
neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a20f465a1f91aa989d6944ca65f29f0a60e2d6975bc15e6370a7f1ca94e811
3
+ size 849280
neuronxcc-2.13.66.0+6dfecc895/MODULE_e60e150057b9b6b21173+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbda94209f8315ff15bba26787e53da2ff462253c56c2228b9a165816456191
3
+ size 6800384