Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
ef21075
•
1 Parent(s): c9cff6c

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/OpenAssistant/llama2-13b-orca-8k-3319/166b139e9e1e2f6bde18.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1038,3 +1038,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_7a197fba279f0fd01e77+2c2d707e/model.neff fi
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
 
 
 
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
1041
+ neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1042
+ neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/OpenAssistant/llama2-13b-orca-8k-3319/166b139e9e1e2f6bde18.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32016, "max_position_embeddings": 8192, "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": {"factor": 2.0, "type": "linear"}, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "max_length": 8192, "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": "OpenAssistant/llama2-13b-orca-8k-3319", "checkpoint_revision": "b02bf240968a60674d9e1afc73f83868ae52fee0"}}
neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc68c84d5cc463d4336ca2d5425ddd500ac27b4113f13282ee81e2d6787289d
3
+ size 436608
neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930ae599fed2e54cb23314360ddea92cce966f558c127d59b38912b40747d6cc
3
+ size 56167424
neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c9e7fc26300e45dd526f03d034e3df12b3405bb1f613937b06c638fd82d7dc
3
+ size 492467
neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4b618e3a0e15aa8795fcf36c69ac20546f28fe2d7a7616db1c67c5bd630091
3
+ size 7947264