Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
267
dacorvo HF staff commited on
Commit
608a595
•
1 Parent(s): 357b3b9

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/meta-llama/Llama-2-70b-chat-hf/bb799f26ba52a99d8a74.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1138,3 +1138,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.neff fi
1138
  neuronxcc-2.12.68.0+4480452af/MODULE_101d6badbbc22d979db6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1139
  neuronxcc-2.12.68.0+4480452af/MODULE_96c74602c6595c924750+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1140
  neuronxcc-2.12.68.0+4480452af/MODULE_b731fc0c29ae932dea47+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1138
  neuronxcc-2.12.68.0+4480452af/MODULE_101d6badbbc22d979db6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1139
  neuronxcc-2.12.68.0+4480452af/MODULE_96c74602c6595c924750+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1140
  neuronxcc-2.12.68.0+4480452af/MODULE_b731fc0c29ae932dea47+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1141
+ neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1142
+ neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/meta-llama/Llama-2-70b-chat-hf/bb799f26ba52a99d8a74.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": 4, "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": "e4b287212771ce25f782ed8636cbea2d7c5ac7e2"}}
neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41db95487aa4e0dac2042f410b50ac24570e171d67d108d5eef2651f1d3b107e
3
+ size 879680
neuronxcc-2.12.68.0+4480452af/MODULE_2cb27cadb7611533cd4a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e852ed33a8d0b004264bc54fed0462b1917f38236b6de98f7a027a785b5d4c7
3
+ size 113675264
neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74875ee96894121149cd47f0cab2d060da5931edca35e887a0fe484191c871b1
3
+ size 993909
neuronxcc-2.12.68.0+4480452af/MODULE_8591d903dcf8b6e2b00a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610b53cf392e3c7f4859c83b1d59ee3be5adee6b5ad5af1ec0b387f3ae0353d4
3
+ size 14193664