Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
dacorvo HF staff commited on
Commit
241945e
•
1 Parent(s): 8f48f2e

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/b9d19496a7bb0ea12bd3.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2650,3 +2650,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_c53eee71989415a8300f+2c2d707e/model.neff fi
2650
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d10e396f3ce809aae550+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2651
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d5e5e35c4b9105b69867+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2652
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e9f964a925c5418d1e93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2650
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d10e396f3ce809aae550+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2651
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d5e5e35c4b9105b69867+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2652
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e9f964a925c5418d1e93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2653
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2654
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Meta-Llama-3-8B/b9d19496a7bb0ea12bd3.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": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "abf8f1bbc9f1ceefa4e88667311436858dd75de0", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "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_5f931e8bf304c87202cd+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c10824ee0aec23fe6fb20e57194991980472a6d20577b9ba0bbe7e459eeb7bd1
3
+ size 343832
neuronxcc-2.13.66.0+6dfecc895/MODULE_5f931e8bf304c87202cd+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f3d928976f26bbeff8dd9554a1b05dae345576b55e5d0806459771d4bb6d0f
3
+ size 14449664
neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890f1add7015bffa50f6ab8ce1d26a4741c0c0abd19a9703a59a80402c4aa986
3
+ size 397220
neuronxcc-2.13.66.0+6dfecc895/MODULE_a4fe1c700a9abdb20641+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16934039407fc7a101d0b509fadaeb7ad602d1f865937565749df3ee16c6d7ab
3
+ size 12319744