Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
56528f2
•
1 Parent(s): 473fc3b

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/bcce81dc6dcb5f751067.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1072,3 +1072,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.neff fi
1072
  neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1073
  neuronxcc-2.12.68.0+4480452af/MODULE_6ce450eeba84f8c95243+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1074
  neuronxcc-2.12.68.0+4480452af/MODULE_983f893836a08abb88b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1072
  neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1073
  neuronxcc-2.12.68.0+4480452af/MODULE_6ce450eeba84f8c95243+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1074
  neuronxcc-2.12.68.0+4480452af/MODULE_983f893836a08abb88b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1075
+ neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1076
+ neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/bcce81dc6dcb5f751067.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3eafa4deb50cb91a5a9d53a23dfe49aed0849a4836c6488240ee90996c258ed
3
+ size 350447
neuronxcc-2.12.68.0+4480452af/MODULE_53b2801b6ef3fc3e1eda+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ab5505d973528273d809adf3c43cdb69ccd4e6671efac0c3e0545ea9e1c0bf
3
+ size 18914304
neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76258fb92f69abe1f761224882d94ecacda799682bced4152470a6439e7871a
3
+ size 395290
neuronxcc-2.12.68.0+4480452af/MODULE_bfed690b3cc418fa6c00+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc7f36ae9f5db1b45fa7e7eb62a598975082ddc2564315391bbd69978526a4d
3
+ size 5571584