Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
239
dacorvo HF staff commited on
Commit
c9cff6c
•
1 Parent(s): f3afa61

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/inference/llama/meta-llama/Llama-2-70b-chat-hf/225d9a4eb91175602e94.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1036,3 +1036,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_836b3660ff8225436598+2c2d707e/model.neff fi
1036
  neuronxcc-2.12.68.0+4480452af/MODULE_b2c7ce1076a6f000e232+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1037
  neuronxcc-2.12.68.0+4480452af/MODULE_7a197fba279f0fd01e77+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1038
  neuronxcc-2.12.68.0+4480452af/MODULE_9b4e781d84e3ad27ec93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1036
  neuronxcc-2.12.68.0+4480452af/MODULE_b2c7ce1076a6f000e232+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1037
  neuronxcc-2.12.68.0+4480452af/MODULE_7a197fba279f0fd01e77+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1038
  neuronxcc-2.12.68.0+4480452af/MODULE_9b4e781d84e3ad27ec93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1039
+ neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1040
+ neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-70b-chat-hf/225d9a4eb91175602e94.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 8192, "intermediate_size": 28672, "num_hidden_layers": 80, "num_attention_heads": 64, "num_key_value_heads": 8, "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": 1, "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-2-70b-chat-hf", "checkpoint_revision": "e1ce257bd76895e0864f3b4d6c7ed3c4cdec93e2"}}
neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06157f3decb4566de534305791bfd91268f7341b78f3ae1ef85b0be3040a25e6
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a0e1246835cfa636167644a1ab7471a1ce99232ad602b693f62711988193c6
3
+ size 10056704
neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7152fef6df2f275d6e2950939ba4cce8d84a34854077cb07cb24e6668652fa54
3
+ size 747948
neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4b98eaa460ba247b40bcacaa1b9e1acb6ed8cdde8f565cdbfc275ff5d6167c
3
+ size 53269504