Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
242
dacorvo HF staff commited on
Commit
aafcbb8
•
1 Parent(s): e4fe46c

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/mistral/TencentARC/Mistral_Pro_8B_v0.1/ac6b3a8357dd0b713546.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1616,3 +1616,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_38a909a9e66906ffe277+2c2d707e/model.neff fi
1616
  neuronxcc-2.12.68.0+4480452af/MODULE_b1779304eead2fd6ef37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1617
  neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1618
  neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1616
  neuronxcc-2.12.68.0+4480452af/MODULE_b1779304eead2fd6ef37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1617
  neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1618
  neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1619
+ neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1620
+ neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1621
+ neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1622
+ neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1623
+ neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1624
+ neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1625
+ neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1626
+ neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1627
+ neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1628
+ neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1629
+ neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1630
+ neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/TencentARC/Mistral_Pro_8B_v0.1/ac6b3a8357dd0b713546.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 40, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "TencentARC/Mistral_Pro_8B_v0.1", "checkpoint_revision": "366f159fc5b314ba2a955209d2bca4600f84dac0"}}
neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f073480ecd321a99dbc20c0fa0bf4b668c578f25c3bbecda024a61f2fc7e89e
3
+ size 1060576
neuronxcc-2.12.68.0+4480452af/MODULE_080c26f72a442f5dee73+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb832b49b7a9b14927d1216235aebb6a8eea0edca63fcbdf8823fbbf9e626d97
3
+ size 10568704
neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ff6f07c84fcdf2399b593f6c91b241c96ada6b3b4351a8f69e95dedf0ef84d
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_0d4c2b042071a51facc1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62609fe1abcf3ee3d74729dd9e3a1ebaed603b5a0146e749aec63d8d44a8b3b7
3
+ size 9923584
neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a452f393cdd2fbccca2aa6104ed0840aee49c4067aaabed7249e3c4a7ba9a3
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_252699acf0ec2a5d44e0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba0da8282b79fdc9418d52d236c5d1462afc393dfa424e8181fff4d5e38faaa
3
+ size 9647104
neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04e16ed634bdb37aa5d3884df0d9dcd34ad3fb65a3a632c39d62b22ebe22629
3
+ size 10890977
neuronxcc-2.12.68.0+4480452af/MODULE_37a46b889d39790f2ef2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55160b6ccf260b4edebb5e1dd286c6281775320b1f0d40fef4d78c32afc7916
3
+ size 14060544
neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ceb1949450b2982267245eb9acf12f474546a07dff73e2b3092184e870aacc
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_516b2955674be9468164+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57eb7e1cbeb04b22061d17feee8c9744a09c713da00e91e4fa31340ac03d38c1
3
+ size 9606144
neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf80bf8eeb87b070f657bdc78d96af20df8245c0c083f1cd1eb4e6785d4e508
3
+ size 42348257
neuronxcc-2.12.68.0+4480452af/MODULE_5a685a1a29e8e7c93bac+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a5a63238499093db6ffc50e550d9141d5c72180c2d9f07d7aade0830486bcd
3
+ size 33076224
neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73cf11cdd7df4d0265e6756bfa1307b40056020ae7c8f03c38ff109a8041ea4
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_5f1d53d78993e03021ef+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590dbd80ac69e9abdc18d7d83a7868d73dec49b1ce9a55d61ef730682cae728a
3
+ size 9554944
neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdec251d5166a2f670ffecfc9315ec6a0e50e9172335499f99300182a38aaac
3
+ size 168177497
neuronxcc-2.12.68.0+4480452af/MODULE_75e2674fcd1feef17981+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5af8760e150236c680ca1b753b45017b41d3c9b483cbda4d7a0f2c60e949ce
3
+ size 57283584
neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5897e7540ceb3e37deeb48867f782e5ef55bc567507d97273a410f8c955463
3
+ size 3026657
neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21334934327446dd04fa4e58408cae75eccfbb8576162c4f661a3c86fd54c184
3
+ size 11592704
neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c386008f083bd9b063a909200e7ea28c14df0e0f73077e6b866efd9154147a19
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6cd2f08687c4ef76d516514328f4bad775b072d3d737d0e932c1d0383985e95
3
+ size 10363904
neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f93c57bce340f1988c383d74cec6d55bb1dcbf9790a2f39cb4c3ae9eb0df96
3
+ size 397153
neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b63494c8e8cad9b399797023aa78ff1223788f0de0a7660d3d14b99983360ca
3
+ size 9442304
neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9aa2ed473f93d25a46d08972fcf91f7dc2cfd120119585490c7d933ba453e8
3
+ size 563545
neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4c62258793544f7000e1c7719fec5709a401688cb7ff762f155fbac3ad94d0e
3
+ size 9933824