Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
180
htokoyo commited on
Commit
64c3b22
•
1 Parent(s): 90aa5c1

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/elyza/ELYZA-japanese-Llama-2-7b/2fcd59a6a55827d3acf4.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3084,3 +3084,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_80aa9f73ccd44098639e+2c2d707e/model.neff fi
3084
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ef52585a11a58ec648d9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3085
  neuronxcc-2.13.66.0+6dfecc895/MODULE_1576602c59c08787661d+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
 
 
 
3084
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ef52585a11a58ec648d9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3085
  neuronxcc-2.13.66.0+6dfecc895/MODULE_1576602c59c08787661d+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
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/elyza/ELYZA-japanese-Llama-2-7b/2fcd59a6a55827d3acf4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "elyza/ELYZA-japanese-Llama-2-7b", "checkpoint_revision": "976887c5891284db204320860bb84b71d598063e", "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": 32, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9614644d97d613da941f200b7181db238e32a13277666fdb91d7dba25d02f8e0
3
+ size 380315
neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf69ada25028df55bdec898404a5206dc9f8c9b2df7e81a6ab9f32ac7151a391
3
+ size 16016384
neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5620c28a4a6b1541c60462e481cf685e24e3d769d86676a24dc9a4ab52ee298c
3
+ size 335311
neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fdc7e3fc8715379c8c9638ea5e480f160cb929100f3219ba5932e2e2f61918
3
+ size 20337664