Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
4a6a01d
•
1 Parent(s): bc47789

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/ab18a81c73346c9b0e4b.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/model.hlo_module.pb +3 -0
  11. neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/model.hlo_module.pb +3 -0
  14. neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/model.hlo_module.pb +3 -0
  17. neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/model.hlo_module.pb +3 -0
  20. neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/model.hlo_module.pb +3 -0
  23. neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/model.hlo_module.pb +3 -0
  26. neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.hlo_module.pb +3 -0
  29. neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.hlo_module.pb +3 -0
  32. neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.hlo_module.pb +3 -0
  35. neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.hlo_module.pb +3 -0
  38. neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3719,3 +3719,15 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_df8fba2abca3d0417a12+2c2d707e/model.neff fi
3719
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7bd7a2134c7496f5ce9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3720
  neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3721
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
3719
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e7bd7a2134c7496f5ce9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3720
  neuronxcc-2.14.227.0+2d4f85be/MODULE_137c8b8e10ff9b01f019+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3721
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ed7d60702ced343259aa+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3722
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3723
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3724
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3725
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3726
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3727
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3728
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3729
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3730
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3731
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3732
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3733
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/ab18a81c73346c9b0e4b.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": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-70b-chat-hf", "checkpoint_revision": "e9149a12809580e8602995856f8098ce973d1080", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "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": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0aafa8f91bb84c29d1ed16eb384073d965ed2f276ffd0c81f9ff5edf8d0c96
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_02aff787a4873f605551+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7000bd215bf1b53b4675ecaac09a84e362f800eeb90fa520e1e53ee15ab85d5
3
+ size 8541184
neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55650a162f742065b4a212552800226354271e4b40b8c5c8692d080cb72207e3
3
+ size 667140
neuronxcc-2.14.227.0+2d4f85be/MODULE_2fdf2bb9ff400b3d50c1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dfe68269795baaabf9c12108af01529265e7bec74efe2a228665cbce83d37e
3
+ size 4731904
neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff656ef43d05325cf2da55648139fbe69b77d1e0b858a6f7bf6bdaf1bfbdaa4d
3
+ size 667140
neuronxcc-2.14.227.0+2d4f85be/MODULE_8117f55b5862f500d459+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cd558370f2143acfb43b72dc6f3476402b88597e4bd8f4bad61df40c392171
3
+ size 26758144
neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7e4c9a93fd465755a8d12eadb908323c030b4c612425a39b684b7e74532fbd
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_8856fa169ec14278b7a0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21e287b7f1b3bec35f4c334983fece7982a05e06e611555f0c4cd7443132a94
3
+ size 8500224
neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551244f4e204eae9a36f9fbda8d100179ed0023abe7fb1bf7c0a88e35dcdf79f
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_8a1ad08af90a0ab5e148+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5cf26b9365f84ff71ffc67422147c76e13bdff7d23938ad9cf159817163644
3
+ size 8797184
neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352639b780edbe37d48389e520efd8bafa50bbbf771feaf72eb3d7005a8dab8c
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_91978966e6b1119e9d84+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa53691518d8cc9280ec3f7c4c360f056a3c14850f8890f4ad28607e7ad54005
3
+ size 8643584
neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace0cc5b482dd6a7ccd12c1ed8c1c4454f89b43a67e23d397d9305356003f1bf
3
+ size 667140
neuronxcc-2.14.227.0+2d4f85be/MODULE_9780aecbe2eb09a35f5c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb7427ea694f5e5df5c692eb323f62a34197b121727e522f95560e4394394b36
3
+ size 10865664
neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa812ab79c74938ab42d0ad00ea924f5c6dc7b9f51ea258cd85647e31ae6534
3
+ size 667140
neuronxcc-2.14.227.0+2d4f85be/MODULE_a97ca5ff971d68e1c155+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f3d71e6cc71f2e33f1e3965b59bfb5b6af0305a390b25cc5da139c0bb467fb
3
+ size 15012864
neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72371efa6d1adb7604e419b748d0bc8a0ebbaa3c573bf516ffbc25a12d0f9ea3
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_cae03da621199038d158+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668c33de251d7fe9ba2aaa703a4761cd3e878e5f16b2fb962f6a8b93775c017f
3
+ size 9135104
neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60cb1cc722515f56c484d8fcb540c0da816742802c364982cde0caf8c37e4ab
3
+ size 839401
neuronxcc-2.14.227.0+2d4f85be/MODULE_d811ad422fc6e57e2d03+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3cbfb239010f21b229bc14a0695ba4376513cefcdafeee20317cc025a015df
3
+ size 8479744
neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76177608becc9d1f455c506dcf9dfc392029fc88762b56f21e508a914e28d5fd
3
+ size 667140
neuronxcc-2.14.227.0+2d4f85be/MODULE_e7605daedd5fe0be5d0d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b788825719c4af7c5ccc3410fc549d92233e41e06ee83321404e824f72d4f0
3
+ size 11777024
neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24217e40d1101bf7c728a4c69a0ae5fce6962964e07fcd1bea9436bff77561fd
3
+ size 658629
neuronxcc-2.14.227.0+2d4f85be/MODULE_fbb6ab8551395a88e298+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd31c46eb3b8bfd407d6d840e42a6afc65007fc77f61257cb789e11eeea49dc
3
+ size 11777024