Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
e5ad8ba
•
1 Parent(s): 0aeb7b9

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Llama-2-13b-chat-hf/bb021d3936261da2684d.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2871,3 +2871,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_bc55534a8a895d27c96b+2c2d707e/model.neff fi
2871
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dd73cf6430018dbf30ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2872
  neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2873
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2871
  neuronxcc-2.13.66.0+6dfecc895/MODULE_dd73cf6430018dbf30ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2872
  neuronxcc-2.13.66.0+6dfecc895/MODULE_62af34a8b34ede5ed98d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2873
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c5749e13a2312d8b2b31+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2874
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2875
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/meta-llama/Llama-2-13b-chat-hf/bb021d3936261da2684d.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 12, "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-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9221508d31026d67fefed008802ee60d352a5e301fe91a7d472ae05f7015bb
3
+ size 475811
neuronxcc-2.13.66.0+6dfecc895/MODULE_2b1448ef3d191c067d54+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630fbef65de02cd238163c004c1f78d46b8d3df1441609585c795ca567880071
3
+ size 12504064
neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2114810a011bffa0e81e4f9aae08b2aaf8b5e4b4e1d8af006014043b016d211a
3
+ size 419753
neuronxcc-2.13.66.0+6dfecc895/MODULE_45c49db702685a5049e5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472d37a01125fd9c3b3ffd8d20279fdaffba8bda6216ee27027d7489b6769533
3
+ size 6493184