Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
267
dacorvo HF staff commited on
Commit
f8ef81d
•
1 Parent(s): e5ad8ba

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/ee7617214dccb41a3d74.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2873,3 +2873,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff fi
2873
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2874
  neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2875
  neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2873
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2874
  neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2875
  neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2876
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2877
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+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/ee7617214dccb41a3d74.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": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "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_a6ab75863e2bebfd8bca+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef84982c884cef0dd21e0974f55cd6ee891b9ca4b40f1439c91a90ba843dfbc
3
+ size 397220
neuronxcc-2.13.66.0+6dfecc895/MODULE_a6ab75863e2bebfd8bca+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9aa937b4194ebb2480c77fe6f7671b85d0c715a10e6ec0e0ba872b1ca914464
3
+ size 13917184
neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f0778f276d01223078424565f3318ddd59089a305d18fdf6194317b957bcbb
3
+ size 343832
neuronxcc-2.13.66.0+6dfecc895/MODULE_f3d819fdf4e7cc6ba302+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7699f18799c3be0b8a98e56a12c0fe2ae652e71de2d92d58ecc058da6504c95
3
+ size 14470144