Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
180
dacorvo HF staff commited on
Commit
0b6c666
•
1 Parent(s): 4a6a01d

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/Llama-2-70b-chat-hf/044ec5e8a8f4bdfa3487.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3731,3 +3731,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.neff fi
3731
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3732
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3733
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3731
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3732
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3733
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3734
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3735
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+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/Llama-2-70b-chat-hf/044ec5e8a8f4bdfa3487.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": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-70b-chat-hf", "checkpoint_revision": "e9149a12809580e8602995856f8098ce973d1080", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a56de0bc92b718db44fbddb88839a9856cbb7b98b33890c28150c4f1d3be80
3
+ size 907957
neuronxcc-2.14.227.0+2d4f85be/MODULE_72d432e52bbbbacc7a9f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de7899042004906ff61094a584cb6b87f4eb4405536d2d7e0f57daf7c900028
3
+ size 12831744
neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29a72c3aba9caaf16848a2af07f841835d4459532ef5ebc1d84f9baa99a90f1
3
+ size 1116101
neuronxcc-2.14.227.0+2d4f85be/MODULE_7ad53a04217efe4abf9b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9665ffd4f8833d42dd9a08c88bdf5e20116e9806f8db5cd879da93780e2d30eb
3
+ size 8786944