Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
236
dacorvo HF staff commited on
Commit
0593c6d
•
1 Parent(s): 6dd642e

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/NousResearch/Llama-2-13b-chat-hf/b39207446be340f95f2a.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1008,3 +1008,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff fi
1008
  neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1009
  neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1010
  neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1008
  neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1009
  neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1010
  neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1011
+ neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1012
+ neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/NousResearch/Llama-2-13b-chat-hf/b39207446be340f95f2a.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f"}}
neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b8d37a3b5c163d8d776cf3a320cb97b8878b6148a457308ffa3bcba947c8b4
3
+ size 492467
neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b74d11e6a48676361dd018ed6fff46416e736264f8fb9f63c3c26006d5a24f1
3
+ size 7947264
neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371a05603f6f551824e16789274384cad220a33a4ca6361269a35fa33a46989d
3
+ size 436608
neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48352f2a77667f7476d27f942b83e3a59c440f7e0505b4c73d47f804d82aec5a
3
+ size 56177664