Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
htokoyo commited on
Commit
5b590b1
•
1 Parent(s): 64c3b22

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/llm-jp/llm-jp-13b-v2.0/38e1ed12600e4beb0fc1.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3086,3 +3086,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_1576602c59c08787661d+2c2d707e/model.neff fi
3086
  neuronxcc-2.13.66.0+6dfecc895/MODULE_9290f1eed7ff8099bd34+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3087
  neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3088
  neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3086
  neuronxcc-2.13.66.0+6dfecc895/MODULE_9290f1eed7ff8099bd34+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3087
  neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3088
  neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3089
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3090
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/llm-jp/llm-jp-13b-v2.0/38e1ed12600e4beb0fc1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LLaMAForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 7, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "max_sequence_length": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "llm-jp/llm-jp-13b-v2.0", "checkpoint_revision": "1fa7d9406b198856bafe6c196f59290aa400fdc2", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pad_token_id": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 97024}
neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5f81bcad6441ba38d4c1509445be53b61e232b9017b85e3cde903ac71d25c0
3
+ size 475811
neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc54b0dd754c8b30eb38565bdf1d2d6f78df9255753ee743ddb1bccbc949fcac
3
+ size 23890944
neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46607b0ecf919e34fd424bdff98e5b3d1c296bebe8334d7143665a29c7ecc7e5
3
+ size 419753
neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c78db7e7e6ffebfb83992c6275fd23426e1cc12aa2fe23c3d6b06a1f238181
3
+ size 6616064