Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
180
dacorvo HF staff commited on
Commit
89f4abe
•
1 Parent(s): 89f5ca4

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-3-8B/f4d3b8d77ca346e0d21f.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3537,3 +3537,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff fi
3537
  neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3538
  neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3539
  neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3537
  neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3538
  neuronxcc-2.14.227.0+2d4f85be/MODULE_153f2fa90c098f489330+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3539
  neuronxcc-2.14.227.0+2d4f85be/MODULE_41d0c2d541507abdf9ee+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3540
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3541
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+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-3-8B/f4d3b8d77ca346e0d21f.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 48, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 12, "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-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41779387a728ca2a00a817c535b008d5df7709e2f12e257318acf2000b0b7521
3
+ size 337090
neuronxcc-2.14.227.0+2d4f85be/MODULE_0cc9d27248b2b06f3e8d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa55001c81f715af2e0a657512f0ef81db91cd281266d13bf181a5ece1560d6
3
+ size 15340544
neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8458bc272113a2d53457882de8b51806cb237df8202677011de364e4b829f5e6
3
+ size 434173
neuronxcc-2.14.227.0+2d4f85be/MODULE_6eb4c4d0d47f1150ca92+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d0563fe351ad817aaa9f214701d8ae07d4b478053174982c99e1bee87df4ba
3
+ size 27577344