Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
264
dacorvo HF staff commited on
Commit
884fc75
•
1 Parent(s): 7572840

Synchronizing local compiler cache.

Browse files
Files changed (9) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/d7a89fb7e78c11245691.json +1 -0
  3. neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Meta-Llama-3-70B-Instruct/06721e5c307589548b87.json +1 -0
  4. neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/compile_flags.txt +1 -0
  5. neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/model.hlo_module.pb +3 -0
  6. neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/model.neff +3 -0
  7. neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/compile_flags.txt +1 -0
  8. neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/model.hlo_module.pb +3 -0
  9. neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3379,3 +3379,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_d133df880751a3363899+2c2d707e/model.neff fi
3379
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d15731d49b88b4bf51a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3380
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea22347137b0711ac1cf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3381
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f6441c65760e62367b19+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3379
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d15731d49b88b4bf51a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3380
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea22347137b0711ac1cf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3381
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f6441c65760e62367b19+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3382
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3383
+ neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/d7a89fb7e78c11245691.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 24, "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "351844e75ed0bcbbe3f10671b3c808d2b83894ee", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "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-2.14.182.0+a56cbff7/0_REGISTRY/0.0.24.dev0/inference/llama/NousResearch/Meta-Llama-3-70B-Instruct/06721e5c307589548b87.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Meta-Llama-3-70B-Instruct", "checkpoint_revision": "84cbdcd4bcccad50126c29ec7f7a476dec014fcf", "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5921d4bd328f771f8fd88918d926c6832412dacaf53e3a1181347b439cb07aa3
3
+ size 1068664
neuronxcc-2.14.182.0+a56cbff7/MODULE_4ffb5256f850149929e5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212c754b820feb1b24b709a8e88ab08bac0d3f5b145bd01dc9d5796009007f9b
3
+ size 13528064
neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca48d702f5faad940aa245a876e5509dfa6deaa9c158488de84974e59f98f0a4
3
+ size 1283944
neuronxcc-2.14.182.0+a56cbff7/MODULE_c6183a14ce0579154b83+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3995883f7e498aa7a286b2eafdf292cec1bec39a3d7ff7a2e47af11ee2ca26
3
+ size 7977984