Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
58586fc
•
1 Parent(s): 7ebfca3

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/Meta-Llama-3-70B/8a7c2960b8be4869805f.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3440,3 +3440,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_c0209f9183e5bdee79bb+2c2d707e/model.neff fi
3440
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e9fcf9d21bbb642e70cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3441
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fc7bab2aed847ed31a67+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3442
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ffa764237818d906983b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3440
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e9fcf9d21bbb642e70cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3441
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fc7bab2aed847ed31a67+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3442
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ffa764237818d906983b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3443
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3444
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+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/Meta-Llama-3-70B/8a7c2960b8be4869805f.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-70B", "checkpoint_revision": "b4d08b7db49d488da3ac49adf25a6b9ac01ae338", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75557feefdb92f832e117db1ad9dfdc2de55e2610e04296936ef69814982e55b
3
+ size 1116101
neuronxcc-2.14.227.0+2d4f85be/MODULE_3a94fd503bf593d2a510+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a77f762956d1d3856576935d6695b49ceae695d7643513e913319c6bbf89235
3
+ size 8827904
neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96447409444de6cb95d94929d00e09cd8d89f1b6e7e40d2cd0346d02d1f3355
3
+ size 907957
neuronxcc-2.14.227.0+2d4f85be/MODULE_d52d4e47f62200e73036+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475287f3319b118912edd0e823dd1bef85be22f0379c3459f085259014f4a62f
3
+ size 12893184