Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
5904df0
•
1 Parent(s): 51ed810

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-2-7b-chat-hf/33575da1e5e484f3c4b6.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3489,3 +3489,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.neff fi
3489
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3490
  neuronxcc-2.14.227.0+2d4f85be/MODULE_69a674eb927e566cd298+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3491
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ae063fad05e712fcb6a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3489
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3490
  neuronxcc-2.14.227.0+2d4f85be/MODULE_69a674eb927e566cd298+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3491
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ae063fad05e712fcb6a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3492
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3493
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+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-2-7b-chat-hf/33575da1e5e484f3c4b6.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "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_2314fed9f66566a84fd8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a611ae22362e3d6a8b86e37d34b41872c33e51d9b197591e5d832ef9956f1869
3
+ size 433917
neuronxcc-2.14.227.0+2d4f85be/MODULE_2314fed9f66566a84fd8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a17470f8c7e6fe5643616ba187b13a8fb673f1e2fa26aa8cdc7db14a626620a
3
+ size 31130624
neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e4465628ab1f497b5c7a8d4ad35421ab5aed865cfe01dcd5e41470d38e4e33
3
+ size 336834
neuronxcc-2.14.227.0+2d4f85be/MODULE_9031cf66c7d5124abb6e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5673a719fb710b68277ba44790ec0817819a705a73c2b65f93262fbe804a23
3
+ size 5366784