Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
147
dacorvo HF staff commited on
Commit
106e1cb
•
1 Parent(s): 5ebc0f8

Synchronizing local compiler cache.

Browse files
Files changed (33) hide show
  1. .gitattributes +10 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-70b-hf/137153849e81a4e70bcc.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-70b-hf/57dc4df464b0f3e2cc38.json +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/compile_flags.txt +1 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/model.hlo.pb +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/model.neff +3 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/compile_flags.txt +1 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/model.hlo.pb +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/model.neff +3 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/compile_flags.txt +1 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/model.hlo.pb +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/model.neff +3 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/compile_flags.txt +1 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/model.hlo.pb +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/model.neff +3 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/compile_flags.txt +1 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/model.hlo.pb +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/model.neff +3 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/compile_flags.txt +1 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/model.hlo.pb +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/model.neff +3 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/compile_flags.txt +1 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/model.hlo.pb +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/model.neff +3 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/compile_flags.txt +1 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/model.hlo.pb +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/model.neff +3 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/compile_flags.txt +1 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/model.hlo.pb +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/model.neff +3 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/compile_flags.txt +1 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/model.hlo.pb +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/model.neff +3 -0
.gitattributes CHANGED
@@ -936,3 +936,13 @@ neuronxcc-2.12.68.0+4480452af/MODULE_d0938a1bf4aafed083b4+2c2d707e/model.neff fi
936
  neuronxcc-2.12.68.0+4480452af/MODULE_d4ca6ba52e0580845391+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
937
  neuronxcc-2.12.68.0+4480452af/MODULE_dc22d41775497be14dca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
938
  neuronxcc-2.12.68.0+4480452af/MODULE_e55471efb869a648d6d8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
936
  neuronxcc-2.12.68.0+4480452af/MODULE_d4ca6ba52e0580845391+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
937
  neuronxcc-2.12.68.0+4480452af/MODULE_dc22d41775497be14dca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
938
  neuronxcc-2.12.68.0+4480452af/MODULE_e55471efb869a648d6d8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
939
+ neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
940
+ neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
941
+ neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
942
+ neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
943
+ neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
944
+ neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
945
+ neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
946
+ neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
947
+ neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
948
+ neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-70b-hf/137153849e81a4e70bcc.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": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-70b-hf", "checkpoint_revision": "90052941a64de02075ca800b09fcea1bdaacb939", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-70b-hf/57dc4df464b0f3e2cc38.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": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-70b-hf", "checkpoint_revision": "90052941a64de02075ca800b09fcea1bdaacb939"}}
neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f15ac1fd366e7f8a78bfc72d9596c96dea7ac2b931c1b1cfad063366d1e5c7
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_2aafd7f1f539c16f9649+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7389c024a2d0c38743150758afb7c12632ddf561d1008c251d127af9ab13e8
3
+ size 8858624
neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a2413a3c5ff33703c6b487813d499dbe676ca1d0aede784b1d58f146cf9c8b
3
+ size 747948
neuronxcc-2.12.68.0+4480452af/MODULE_3f7073201620d46f696e+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3978e2ec4ae87a2a4eeefd0f52a44f9173ed5be5001a4384d2c18ea9bee31588
3
+ size 10691584
neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b628a8f08fb32c309dad40e30c05619139c3cc04f72b6cbea9a2876d2921658
3
+ size 747948
neuronxcc-2.12.68.0+4480452af/MODULE_40a45ec1502326fbb3ca+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de6a95e1b6b4706f1b3090457e403e005317fbfce8b137f8de10102a9d45662
3
+ size 11981824
neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b50497c532dacc0ad485a02d0f4f9a6be07b049a0e490c0043b819fb7502386
3
+ size 747948
neuronxcc-2.12.68.0+4480452af/MODULE_8c84d43bf8c883b7cd69+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:387b7fdf55ab1c88cb352dcef7be4d0cb0e6adc967a492f463473b63e4c21d09
3
+ size 27986944
neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0025a67dea8c35742b707af377126aa4df718e99408830a298f6941fb960dd
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_aebb4609c4668acf5e26+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd9deb9767a21d3f2201036d70b696fa27d563ca3f9615eaed8bfc562354afe
3
+ size 9165824
neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e6557f531526dbc45bee607d692281ad7826287dc75253acc3c895dbd930f0
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_b4f3f758f1a1d3abacbf+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcb7c1e466b8568eb974696d74f0b2ec209dced46e7f57fb482539a003073e5
3
+ size 9032704
neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e06379253c4d9999eb96a4f59a7fbac87e939555f651875632101adc08fcef8
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_bcd5e1c88c6f267899f2+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625440a719bc8943245bb65ef6e990bb183abe0596132608d529a68701623dfe
3
+ size 8930304
neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121269d497c80cf23315fd838a4646887c4152cf31e7c6cb09aa91e266ce21ef
3
+ size 756689
neuronxcc-2.12.68.0+4480452af/MODULE_cc88fcd266266515d56a+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6813a6250bd11ceebfc607d8cf185ea5a37c8f7b25895226f4e0d4b5f668b585
3
+ size 9534464
neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a0468fa86b6432bdbafadcd24edcf3e72fe678d67dde6259f51865c7be4171
3
+ size 738797
neuronxcc-2.12.68.0+4480452af/MODULE_e5ea2e91b07024a4c5a6+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801b5f85ba3d44560c9506889b3a9ff3562baba0c3217df1180342e9ef4c356b
3
+ size 10118144
neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --enable-mixed-precision-accumulation --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b622d4fbba91f3c25a13a10f2c16416737cc427cf7ac7b34e20336fa78ffa2ab
3
+ size 747948
neuronxcc-2.12.68.0+4480452af/MODULE_efd165bd378d3b8e92aa+ce379c2c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8f06aa1612b4cc0e854afb24024831d4662253f878f93ce254be9b78a69f73
3
+ size 18535424