Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
cd7745b
•
1 Parent(s): 5a83a6a

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-2-13b-chat-hf/670388f2bc4b70f03ab8.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3533,3 +3533,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_84e79569f870b8449513+2c2d707e/model.neff fi
3533
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3534
  neuronxcc-2.14.227.0+2d4f85be/MODULE_53340fb9d4a801aa9442+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3535
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5a7d974580d76a363137+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3533
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ba1bd8fd45d95f066afc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3534
  neuronxcc-2.14.227.0+2d4f85be/MODULE_53340fb9d4a801aa9442+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3535
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5a7d974580d76a363137+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3536
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3537
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+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-2-13b-chat-hf/670388f2bc4b70f03ab8.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": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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_6d376554828b462d6a32+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf83c7b46ef335f323fb6bd9eb37b314cce08e5430ac65b9990e9408572b399e
3
+ size 422165
neuronxcc-2.14.227.0+2d4f85be/MODULE_6d376554828b462d6a32+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902b79d4e691f3b4f1ab8f44055cac4bf63b73c284ed95511d682ba3e73d1a5b
3
+ size 9636864
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea82eb16e9f6b588cced80111610cc50a5d8661e758288fe17d6a68b41faf14a
3
+ size 543422
neuronxcc-2.14.227.0+2d4f85be/MODULE_c8afc01f6e770b3d1648+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67475b86a1c7cbe07c437c0947977e603094cae77b7ab06d91c051c9ef8ad1ad
3
+ size 29901824