Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
275
dacorvo HF staff commited on
Commit
08cf81e
•
1 Parent(s): b91f644

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/2bdc0ca174bb925d4e70.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1403,3 +1403,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_d0d67b2cfabcfdce1cb2+b48e7cbd/model.neff fi
1403
  neuronxcc-2.12.68.0+4480452af/MODULE_d3842ca8a4530f41526e+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
1404
  neuronxcc-2.12.68.0+4480452af/MODULE_db8b3ded0c7649bb58a2+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
1405
  neuronxcc-2.12.68.0+4480452af/MODULE_fbdbc03bf516fdbd9012+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1403
  neuronxcc-2.12.68.0+4480452af/MODULE_d3842ca8a4530f41526e+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
1404
  neuronxcc-2.12.68.0+4480452af/MODULE_db8b3ded0c7649bb58a2+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
1405
  neuronxcc-2.12.68.0+4480452af/MODULE_fbdbc03bf516fdbd9012+b48e7cbd/model.neff filter=lfs diff=lfs merge=lfs -text
1406
+ neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1407
+ neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1408
+ neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1409
+ neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1410
+ neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1411
+ neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1412
+ neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1413
+ neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1414
+ neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+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
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/2bdc0ca174bb925d4e70.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": 2, "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_08f2730e0347ba68bdff+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca66b1255090d28461d1fb44a6ef6a7e4c12593d0fcc9f0c1c5be112c04ea910
3
+ size 452964
neuronxcc-2.12.68.0+4480452af/MODULE_08f2730e0347ba68bdff+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfa138902b8782e9a7ad8f73577fa8d5d6fd8dd53f85bfe25d8675afc4da4b3
3
+ size 11531264
neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d5977fe202fa8f8026210e181aa22daaddf0daa61425d9fac4ec62e4422e9b
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_13ea32fee9541efe5159+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94c2145b5efcb15278ffb33d0290e3d2a5ec0ad2b04d36809161edf8d5251e3
3
+ size 11643904
neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cceab6dec8e70d3c2d9fbab53c209d0f57e7414b954ed30dc7a07b3a5f6f4cdb
3
+ size 458661
neuronxcc-2.12.68.0+4480452af/MODULE_6df24c0d28c4a8d4bd54+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7f586dbaad4ce70e16c4c54a322ce3f42734181f685b669cca880d769b6991
3
+ size 12196864
neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63bd09387800eeb966ee6a887f417bd7553ed03dfadb50d2c8383c4107db646b
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_82d255632e5c45b293d1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77824231ebfccfee4e2c9cb5cf3bd4e62bcdd09f6bec989876ffe88f836d44a5
3
+ size 10988544
neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ad23f3419fa6e59aab44fdf06608417b00a87cdd257a0fa9a535383457d710
3
+ size 458661
neuronxcc-2.12.68.0+4480452af/MODULE_97c3ab78843a5ce6857c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17af6c87639e5698afa1d214a69ed7dde7795162617fc5eff7f74cf866efe364
3
+ size 67062784
neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43297920a18b68fbb5fe90fabc7edadddd449c1ba1b7d16b311949f9dba5649a
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_9a3e76b710ee8d9d5804+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2375886a86a72cb2aed13322ff9e6511918513242a144e73c27a465ac76ac101
3
+ size 10906624
neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13d1a5a85ca274cccab6e048716b33f98175df85db27f8d0cc3a1dbf18dc241
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_9bd19cac73ed15700a33+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58cd766932e97255ce487b9d63728a9d9812a920e78e8000800c843cef4f69b1
3
+ size 12360704
neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e911c5ab919e5abe424974730af59f21ba127477708bbc19102f698e3dbb9c
3
+ size 458661
neuronxcc-2.12.68.0+4480452af/MODULE_9f5a156beca8c03f02a7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03398fe20039a49ccef6f4637278e784e0a2816e37455985685bfe1b3620a434
3
+ size 16497664
neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49c37d8686d45d2b2ee12ba2e7780c4a94925b0ce456c9500fd1701767debf6
3
+ size 458661
neuronxcc-2.12.68.0+4480452af/MODULE_b7e6a002c959392006c1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b712225eeceb410214343354f4e4222bcf2d28a8c59b4e6d21a6140fc51eea5
3
+ size 13251584
neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5158af234824f624c832c4abf6aa58c1a49d313e06ff59f10522ddcef90a4243
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_d36b31944735d096d3ab+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b3cee4aaa2abd03ecf009eb6a5fed532432ba492d9bffebc506928924c829f
3
+ size 11162624
neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d908c720b91f4d9e5dd2643f8cdf829dc0be7ffb1e42bd8679b275d9dee29af4
3
+ size 458661
neuronxcc-2.12.68.0+4480452af/MODULE_de8351a15ac541d692e2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef99bce2f3c880f16882719a13bdcc92589d85778a52d346bca8f7b4ab2de9e1
3
+ size 34591744
neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f12c7c9bb9d4147f55789a006bd4add942b479253ae952cfc949e0c6d992f1
3
+ size 476310
neuronxcc-2.12.68.0+4480452af/MODULE_f22bfcc3ad4532b97c99+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764c5416d69cf62911b5f68c98c2bd425506846a629018acc1a7cd0ac475f4a3
3
+ size 10855424