Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
34c7318
•
1 Parent(s): 08cf81e

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/d326b9d65c1f7890ab01.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1415,3 +1415,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/model.neff fi
1415
  neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1416
  neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1417
  neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1415
  neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1416
  neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1417
  neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1418
+ neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1419
+ neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1420
+ neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1421
+ neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1422
+ neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1423
+ neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1424
+ neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1425
+ neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1426
+ neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1427
+ neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1428
+ neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1429
+ neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/d326b9d65c1f7890ab01.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 64000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 48, "num_attention_heads": 32, "num_key_value_heads": 4, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "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": "01-ai/Yi-9B", "checkpoint_revision": "58cdd0b4d4cdd2189bbf29a5773c73926084b753"}}
neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e3d5788281d43add195b5ce120f9443bb05e00d9a8fa1cfb26c316062e4843
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_042cef4c14031e372e8e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43972dd7cad1f5c6b242341c41c62a955d150e1b52ee9d8520b4955044bc5f52
3
+ size 3277824
neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2476098f665ac999de900a30173c38d82cc0f102760ffb629e935c20ea94d4e
3
+ size 446460
neuronxcc-2.12.68.0+4480452af/MODULE_13acd7d91ca5a4a76655+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c7a25d3148ff3992d0b09a03a8181c7537f125e931eaf929657ff6126e4c93
3
+ size 20255744
neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6d0b510097dc6cc510abc794a89f316590b167f044eebf29f716ef980bd7e0
3
+ size 440955
neuronxcc-2.12.68.0+4480452af/MODULE_1b0c3318cbe39e15f5e5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db177f034288041e05d949ad45c969a6f6bd35d3df2b8fd8e37dc13d8a6d76b2
3
+ size 3564544
neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acd045e05a8e7b29b8862a697d49d85cd7e3983543067115ff3c5f25c45314d
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_42a807dea3622b805b46+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dfb4a2595e176459f40295c67bb22e0b58b57bc94d6d930a5665d198d4ac2ea
3
+ size 3421184
neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b17982e10041c7299a8d418e969b67235e6fe036ef0f9457de7047f5fe50ca
3
+ size 446460
neuronxcc-2.12.68.0+4480452af/MODULE_5e08f25f7ed898b9a467+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6dd07df35c70191a96464da94e20abd2c973761a8f556a33481fae9ec153d2
3
+ size 9667584
neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a435a296debf88283ff6d103aa294f5853fd0fe6fdc0fde5b3c1f432c1e04a
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_6b594b1def416a3e5584+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f0ed5af0e6f93d04dbf81c22be98b3cb5ae2f1c2c6864852691e8b51b0fd24
3
+ size 3605504
neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76868aa1af65ef2fd776c1079da67a6359f1b5e063b3b5f9d62e13eceb392962
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_8c7dea543fa04f2ad28c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f30870aff11c57794441e6743c44a3c54b691ed52e02ffd4dca058f8dba42d
3
+ size 3236864
neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e666c08a656d15ceadc6223217f1e320621dc565012a77ceeb6d6b77bf8a403
3
+ size 446460
neuronxcc-2.12.68.0+4480452af/MODULE_a1f6f7c054bc7b506b2c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591b192e96f44cc4578ac14843dec92b5d69ede5e4e827229f6363bfc0e9597f
3
+ size 4342784
neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ac20dfecbe51610b857a14d46c78bf1e5a81f90641a098d42962f0b8976556
3
+ size 446460
neuronxcc-2.12.68.0+4480452af/MODULE_a6d3a23b3e4ac68e6613+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662eb09ae362ab258d4b4c3d59a82203068c2d9853831d1a116db62276ee1adc
3
+ size 5243904
neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0fcc8866cdab5b5a9d80771be69d1a3763f7b1fccb565374100808c80a69418
3
+ size 446460
neuronxcc-2.12.68.0+4480452af/MODULE_be996ac6634b66939c9d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88af6eb972e450590e26bf61aefb45de59b2fbcdb71ba111d11cb79dee9399a4
3
+ size 3871744
neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56817e5f5f2a86d7e106c1d0f9a057ee9a159293e4669e2f52d35e171e66822
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_dc5efdc7472d562004f4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b0ff144127fdd9903043bc19cb3ba9a84a9c359866d7bfc5949940c25a10869
3
+ size 3318784
neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d2cd39317b88a93b39c0f6ee380b284e3df49483745c2ee5bf589cfc5ad292
3
+ size 451533
neuronxcc-2.12.68.0+4480452af/MODULE_ddc011feb1b492b1ae0b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcb71e9cbaa7ab8297025900a4022d7f6843e761a6621d0f9cce24aed175eaa
3
+ size 3994624