Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
201
dacorvo HF staff commited on
Commit
221201f
•
1 Parent(s): d12164a

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/01-ai/Yi-34B-200K/4dbc1484f4f8fac732b3.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/model.hlo_module.pb +3 -0
  11. neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/model.hlo_module.pb +3 -0
  14. neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/model.hlo_module.pb +3 -0
  17. neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/model.hlo_module.pb +3 -0
  20. neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/model.hlo_module.pb +3 -0
  23. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/model.hlo_module.pb +3 -0
  26. neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.hlo_module.pb +3 -0
  29. neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.hlo_module.pb +3 -0
  32. neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.hlo_module.pb +3 -0
  35. neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.hlo_module.pb +3 -0
  38. neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3691,3 +3691,15 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_d0c2f720a24a12e1f476+2c2d707e/model.neff fi
3691
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f45e9672dd128b75644d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3692
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5eb6aefdf1e09e28fba4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3693
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eff65bdda486bfea7b7c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
3691
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f45e9672dd128b75644d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3692
  neuronxcc-2.14.227.0+2d4f85be/MODULE_5eb6aefdf1e09e28fba4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3693
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eff65bdda486bfea7b7c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3694
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3695
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3696
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3697
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3698
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3699
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3700
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3701
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3702
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3703
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3704
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3705
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/01-ai/Yi-34B-200K/4dbc1484f4f8fac732b3.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": 7168, "initializer_range": 0.02, "intermediate_size": 20480, "max_position_embeddings": 200000, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "01-ai/Yi-34B-200K", "checkpoint_revision": "7c27c5cab0f5675edc0d9910769d0a6695ade7c7", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 56, "num_hidden_layers": 60, "num_key_value_heads": 8, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 64000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e938428ea979a43db01b094b71b3cd558d5f9bf6c52b451e8d08311c0588beb4
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_025ecf55b8904b835d5d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff212671422d10345086ae9b55b5441dab3789025956a69de4b06254c02e79ad
3
+ size 4987904
neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e183b19ec49ddbe2c93b74b3ef2c76cd6f170acfc5571d99d241945c671617d2
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_11eda2ea777c03ec97f6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7a3dc5524dd4544f8b9fe9d302e1b175a791ded18457b7235604808fc459f5
3
+ size 4496384
neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee69cdb72d55e6147a2f4123099466493165c369905d68c0bac5b2f6f4805c20
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_1c60f13c88d70f462302+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f27304d9345f4d231cc306c944b5dfa1b90e2c8c4b6be624e099bebf7911ce
3
+ size 4568064
neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2ec1f02d824289d452895bd843065dce5df09e4ba963f2f05fdbce368e7f6d
3
+ size 494116
neuronxcc-2.14.227.0+2d4f85be/MODULE_649a857a219203867c21+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e8be4d27254331332c0dde4afabd551e3316f28f46793fc68bc5b8e4b374e5
3
+ size 6401024
neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9340f4233411b3b04f9804d4cff30d8366ea7a4828d90556e55114002a672e9c
3
+ size 500507
neuronxcc-2.14.227.0+2d4f85be/MODULE_6ef9397f21cc871996f5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f805b7cc7d45e91ed8893360d9fc45d2e884917a3c401c5fed0ec4980e0f0e
3
+ size 8612864
neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904c9d7f3d7b78bd1aa66f7b35332be8a64d9b47b0b68e711818e1ef949822cb
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_8261e8a820e5f80bef14+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd89faf630fc17e42e38b8e63530aeedb54ebf19491a4a7c2df7366c67aecab
3
+ size 4649984
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6989414b380cc116f5dbfea928b42283660901eda7fad86ebe6403d43dfd195f
3
+ size 500507
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e77fa5bebc16727a46d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f366d84592289e91e50ed2c68cd1e1d21b13457298250eb8958bf4b0f0507c99
3
+ size 6902784
neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58aaeb85b40045307baacf78b7b7b935660df5bff1783e0c4c782d5dd5ba957
3
+ size 500507
neuronxcc-2.14.227.0+2d4f85be/MODULE_ac86094c38817d32e7cf+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1262adae0ea16b76173f924a3187e916a476e5dac0b79c07c4531f094154f816
3
+ size 16129024
neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8415ece8b451d2078136bfac5f7e94c96c01a31baf43f47e6401ef28fa6d2e35
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34eac338dffe1ea9809c0e308f0423ce91581a42ce3d0503b670c426e9b29463
3
+ size 4537344
neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc18f2089bcf270a15f26efb46dcbc8bde162a50a86942e8fc3065112da43bd
3
+ size 500507
neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8773af96d89ca116253a7176e7c46dcb2b937f6a4a7f9180b8a9086d7302f5
3
+ size 5766144
neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874719401d43a06631749f242540f1a46f55592d85a46073f87ec69a74cb2dcf
3
+ size 627268
neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a9820e9ad32796f1016a187ea86ec1749e85d4fd3cfb1eb2a1b35e7fe2e32b
3
+ size 4762624
neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e4f80952851d2959a3e30dd7213267cdc464b753e979ceea5d49a68aec6f24
3
+ size 500507
neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f2c4462c0dae04bc1f1d9b022e5e981c01f630c4c9c502391d1c365e8e06b1
3
+ size 31366144