Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
196
dacorvo HF staff commited on
Commit
54a23ee
•
1 Parent(s): 0593c6d

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/d004f570f1ef139d9aa4.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1010,3 +1010,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff fi
1010
  neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1011
  neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1012
  neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1010
  neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1011
  neuronxcc-2.12.68.0+4480452af/MODULE_84c4c2f1cce482b43845+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1012
  neuronxcc-2.12.68.0+4480452af/MODULE_f403203d7e9eb8117704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1013
+ neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1014
+ neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1015
+ neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1016
+ neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1017
+ neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1018
+ neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1019
+ neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1020
+ neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1021
+ neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1022
+ neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1023
+ neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1024
+ neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+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/d004f570f1ef139d9aa4.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": 1, "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_142005b3d93076706472+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2816b10dcc5107592b5bd8fbb9b828cef19ae6a6dc281edfce5c134ea8620073
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_142005b3d93076706472+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30cd87e703205ffdedee25b129969c8595f0871ccbad0d64a50fa0205d011b4
3
+ size 2274304
neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069bc855215002ad4f29ae20d3c0cd082bbcda7d16f8c8ec12634a88a46afba7
3
+ size 298010
neuronxcc-2.12.68.0+4480452af/MODULE_312cb57ef1e4a82c10e2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1150e5f7eac6b772bc0383ff4f391a358cf1487c00ff7a22166c1daf8c9022a0
3
+ size 2632704
neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1198516dc0a04ce8100566e92a36c55a3482bf2df4d260404378f97f3b671833
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_686010d205bdde7a4ca4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c119468d0cec18b30f50c74ba06c7ae45d12b01df39a274fce628f2fe5eedd
3
+ size 2243584
neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0e8008a1766163fc64101bed6fcafbe9fbf64e0b83f3ab20b24d877418c588
3
+ size 298010
neuronxcc-2.12.68.0+4480452af/MODULE_7286b801a61423c6a95d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfd43fa37f50ccf0810f12fba6508157de6669c9b576dcbcb802017285800e2
3
+ size 13773824
neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d585a37e5f6abcc58a0fe1248ac1c83c8f99d941679c440afdbd87fe966a03e
3
+ size 298010
neuronxcc-2.12.68.0+4480452af/MODULE_85b81fab23db1bed3d76+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb5289b9eb20f88dffb5006e5ce19e6fcf3365473dd1c34da71d4db96ec6ded
3
+ size 6523904
neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194c127106579f1acefd6d5e9eb3a10d149dd907c61add23587d2217300fc038
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_89ae8efd1a6f9c6d512b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5294e1ac4e010ebefe56628f7960cc5189a524f960a8d9c8d2c6d5b7d79e5d6
3
+ size 2735104
neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03aff1b9f09c44e00712479da882bd444f4f7b1694c33d9dff9d65b2a85fb04e
3
+ size 298010
neuronxcc-2.12.68.0+4480452af/MODULE_8e9fb541306b8a41398c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb5da7f37e7e02a36089ba1ad50a22f1059128f71d914a0ad7129e3e6d5031c
3
+ size 2939904
neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78f28a5ae634728e5b316ca6c159365660d44410a6f1f5bd322666557bbf2a4
3
+ size 298010
neuronxcc-2.12.68.0+4480452af/MODULE_daddbb4b40f42fc0d4bc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fa6d68630716f4bcdbfaac2f6e8bf1ce82df0722a625c025e629416e0aca79
3
+ size 3564544
neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c14a9d26acac2591732513766f7c30513d16521bd37d8e0558d754fb23d27d
3
+ size 294331
neuronxcc-2.12.68.0+4480452af/MODULE_ddad033946b031c38e61+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51052554ee40488b3efd014235b7b2e6a50587617a1727b4ed91b6355bd80745
3
+ size 2427904
neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1a4791b628a1f524b525d1c3fa869911ee518654cab7269b43e836e7ed6dc3
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_e0f8532800e3830d9976+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a3391653967ce716e3559ba97b3b7e8045e385dc5e4d41fb09fc7ca07ad9cc
3
+ size 2468864
neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94119b3c954782d68baa9f1cb08d6e4d2ca77c9eae9803efa2596d77b7653ecc
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a55125098f125b171e4e014833854a9ad61c5812c2adef9114783173f7c1f8c
3
+ size 2223104
neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cb251577a3fd35f0c3c558668e48ab35170aab01c0fe62e7170bdeb06dc138
3
+ size 301369
neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e995f84912e3bb6755a44f32de425f9a524d692b286bac597a62fdd7302abe9b
3
+ size 2335744