Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
213
dacorvo HF staff commited on
Commit
f5be8e6
•
1 Parent(s): d0bd710

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/0b62266eaa9ecfdd4c4c.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3140,3 +3140,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_2745e2a360eb982e261d+2c2d707e/model.neff fi
3140
  neuronxcc-2.13.66.0+6dfecc895/MODULE_67a4d1fe61d13931853b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3141
  neuronxcc-2.13.66.0+6dfecc895/MODULE_47991e7bed6610af26d7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3142
  neuronxcc-2.13.66.0+6dfecc895/MODULE_6b094a2ea2d3f54879b4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3140
  neuronxcc-2.13.66.0+6dfecc895/MODULE_67a4d1fe61d13931853b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3141
  neuronxcc-2.13.66.0+6dfecc895/MODULE_47991e7bed6610af26d7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3142
  neuronxcc-2.13.66.0+6dfecc895/MODULE_6b094a2ea2d3f54879b4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3143
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3144
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/0b62266eaa9ecfdd4c4c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "83e9aa141f2e28c82232fea5325f54edf17c43de", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c96ae2856d00a2258acb836c52116b56adddfcec0ea65c5daff20081eef0eb
3
+ size 399416
neuronxcc-2.13.66.0+6dfecc895/MODULE_2920d83bb25b02e4cc51+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f303e09fd73d71c162093b9decea9d5d82d9c7758c2ca5c2d40a0c50ae840c31
3
+ size 5755904
neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a66a1e291890013fde5baf0b47acd53bb97677e14f4c159584dfa775a7224b
3
+ size 346060
neuronxcc-2.13.66.0+6dfecc895/MODULE_50a1588f6cf69a2eec93+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16651d24afce0dce5df6c4830c43e322c02c37f8b8b481ae0f6126891eae5533
3
+ size 30516224