Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
e38a6c4
•
1 Parent(s): 1a19897

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/NousResearch/Llama-2-7b-chat-hf/7ae7709b5915b3125fb0.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1026,3 +1026,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_13ce0aa1713a6579ebe5+2c2d707e/model.neff fi
1026
  neuronxcc-2.12.68.0+4480452af/MODULE_b9022a7120a9b15abca7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1027
  neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1028
  neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1026
  neuronxcc-2.12.68.0+4480452af/MODULE_b9022a7120a9b15abca7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1027
  neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1028
  neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1029
+ neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1030
+ neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/7ae7709b5915b3125fb0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "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-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8"}}
neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc349adbfecda132f2eb72b05b3a010407bff87f47b4c34fe635d98cad90906
3
+ size 349423
neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99e4085dd49be185f6d1baa85ae3d56a7769e2383c1e5aafa2d4b3ed2607e13
3
+ size 30465024
neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7f52f5d1e15bbda0514ccd1d72a36eb6edd01d486e4f5092fe81622f911362
3
+ size 394266
neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51df8d8813d486fa06480a7633aba236494c38c103efd8d6385dfaa358bb743
3
+ size 4506624