Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
183
dacorvo HF staff commited on
Commit
7a3b264
•
1 Parent(s): f5b8fa5

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.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/25d78386bf1607f07ae3.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1056,3 +1056,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.neff fi
1056
  neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1057
  neuronxcc-2.12.68.0+4480452af/MODULE_c4847663a6c16ddb44bc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1058
  neuronxcc-2.12.68.0+4480452af/MODULE_da93435af996c9259315+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1056
  neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1057
  neuronxcc-2.12.68.0+4480452af/MODULE_c4847663a6c16ddb44bc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1058
  neuronxcc-2.12.68.0+4480452af/MODULE_da93435af996c9259315+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1059
+ neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1060
+ neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1061
+ neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1062
+ neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1063
+ neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1064
+ neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1065
+ neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1066
+ neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1067
+ neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1068
+ neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1069
+ neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1070
+ neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/25d78386bf1607f07ae3.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, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e748acd879ef01ebdb5aa55cc288f0fcefa97f873b92e252dba69fbbebd183c
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_0eefbe1ea116943f78db+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f51a3c4e4d93e56464c8ebfc28f56ce0406f844dda385d8acfecaa777a18a1
3
+ size 1229824
neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df909519c959a146ceb7aadd52486ee415b2cf7396476c794c8bd01a3adbe63
3
+ size 299034
neuronxcc-2.12.68.0+4480452af/MODULE_654bf58515e816add109+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c15e0c8b5fafc2f59540c4b7ae8703787f34a725e567ecd3aaf39f78157bba
3
+ size 1547264
neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf6672da5aa0836c14cab268bde6617e409274b745a29b765ca60fe04b32f6e
3
+ size 299034
neuronxcc-2.12.68.0+4480452af/MODULE_92503e1fc7e9cbf8e9e0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be3920a3e8d779582c27c5329e91e4a587afc48b9c337ca9da781363410ebe7
3
+ size 1782784
neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f853cad3025763505f6479bfa9dcc5be76f3be063446428e3c2a05b5e30a6f
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_938709e4ce13e9bd463f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fcb5a98438eca0a24526388c359ed6e7d8cbcc3dbee87ec546a67603ad7d4f
3
+ size 1332224
neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289884ff65122f79e0947b5af245c01260c41eda4181414009520295e40f2d03
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_ab853fab33da28c1092e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc86671a59540cc77c4fc7cbb5a8ca81f78a80843c7552ef17a12405790400d
3
+ size 1270784
neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6267fe85fc1facf907fde75041eb949b26b797f09cc3d0f4a96e160be18c3c8a
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_ace8e33ed5e9bedef6f1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901c5927aabc2d77b1ecdb315138d4391ce5dab64d1ccfc1f730f67d153b4313
3
+ size 1250304
neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cba8f97fefc62dc62134f9e543fcf8a4922277a3ff85b25b81379f59178364b
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_ae5d6772a3d1f4a67fe4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d4a0441d6e4f66c5981925a7c83797497e0146d4c1c5bddfea7ccd970c65636
3
+ size 1608704
neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec19d1b33b970b8c82a71716a3928a4a05e051ce7a1c56c3997eea4b6e350c50
3
+ size 299034
neuronxcc-2.12.68.0+4480452af/MODULE_b202a8494e6fa17d96f6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec72974891d873fe6a7965b3cf94cf4c925f155c0fb6e5077534f4d8aced47a3
3
+ size 8162304
neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058c3891f7bf53f464de8b4f7e3d5892c04b1d9cdce0b29704316db68f34b55e
3
+ size 299034
neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dbcb2d98cede9eb0556fc97b30ef2c8d45ee396fd35b7a597baf5ef3f036790
3
+ size 1424384
neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab71b2132bcb6a8d07a7a173c3d9190ec8a851d6e5b60b700b4a59380ad96fb
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a287239f0c0c1b3c4e6104842a279069c4804d01fbb024bf9f2495fc319e952c
3
+ size 1434624
neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a20482dba8a655448e5b6e2836d09bfce6b72c33720958ab68228259e8e62e
3
+ size 295355
neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6442fc02486c607587407748fc83cea2ddfdfaad21a7396f2ec9389c9aed02
3
+ size 1362944
neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9fccf8886ec98a64b9b13ca8a9153ba4afe0ce09fec3882829f77fd8b7c16b7
3
+ size 299034
neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1741ce2de47b75369e530d6b0a5cc45121f4242a7b811ac40b5437e593cdfb
3
+ size 3779584