Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
97
dacorvo HF staff commited on
Commit
614194b
•
1 Parent(s): 4b813c5

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-70B/6f7770a84cba973e886b.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2336,3 +2336,15 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_81f056068aa96e6c4aea+2c2d707e/model.neff fi
2336
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b0dbb61cf0c50b2843b9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2337
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c848301184fdcbe620e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2338
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f3c8d408edb5a3789c7e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
2336
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b0dbb61cf0c50b2843b9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2337
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c848301184fdcbe620e2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2338
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f3c8d408edb5a3789c7e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2339
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2340
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2341
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2342
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2343
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2344
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2345
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2346
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2347
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2348
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2349
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2350
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-70B/6f7770a84cba973e886b.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-70B", "checkpoint_revision": "7cde9a27957f27ce5677b1f838ccaeeb69acc8d0", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce4ad0df5f0c19b13c61670fcdf4f36da5b5d40bc82dcc1fae99e64b9a6fde88
3
+ size 747948
neuronxcc-2.13.66.0+6dfecc895/MODULE_02f0beb857665c3ff0d2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a591f7f78d54d01d8311af3c61e193c28676c6d60dda05718a11eeb010ab8b3
3
+ size 12002304
neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c478ef06b1f45207492844d6b77800c5c422183b13846aa50afa88a3a5c49d
3
+ size 747948
neuronxcc-2.13.66.0+6dfecc895/MODULE_4d8082bdc8479f81c736+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc5b0a7a740a7bfcae814a589c8de4f9c7c5c4477ee435fd0a59c84e2202293
3
+ size 3523584
neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8200f71a563bfd4049bc8d59bda75bd9fbaf3397d52f5512cb45ef362868e33
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_55611ec5f28b1680f67b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422aa644b22d7b39e00cee07e8e3016823d82518302df0873c76cc5d471dbad2
3
+ size 8848384
neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14061f4c2f9b26967fa39fd6e201e938be955efaa69fb7434832a6c5db1b3d0
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_58374579c1cbee002e85+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad01dea76f83eb9343376c76d573c92257fe3c2c539211ab5a41029465c3784
3
+ size 9831424
neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c87cc9c125cd501966f21b4cbc37a799647eec252c8a049a62706692569d6c
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_62d4dc73a815ffbc3fd6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc90322fa84b1416aaca73f208a6459f43289a31b95cecc8ab3ce5fda27f370f
3
+ size 8766464
neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ed70fb537a42a54bc3a7f6576b785330acf6b5157e2141b32fcf0f13d88fa7
3
+ size 738797
neuronxcc-2.13.66.0+6dfecc895/MODULE_84559d816feb14b36a16+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13510bed62f37b084fd28ebe9a147f91f26b45116793685ed6a1aeab79a58700
3
+ size 10302464
neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c0c7184f526c5b9a17b4ef86b93c2cf1662207aba45ed7979694c1bd73acc5
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_9e268a3d59d7af020877+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea3b2c467f4da434742269e87dfeec8ebf5070bc040ed645067774d3c5da85a
3
+ size 8961024
neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e412d068e9303fd05376c18c52c748feb2873e57f927eda76966d0fecea22b
3
+ size 747948
neuronxcc-2.13.66.0+6dfecc895/MODULE_b5c580049a37e98e889d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09405a32f74cafe91863a820797d8c8c0cd2f60747b4cd7ba0f6eec71be9f20f
3
+ size 12708864
neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753524d7021ec6dbed9a214bd298a9cde77e7723c5b85b8ef1fac5635d3d8449
3
+ size 747948
neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91052f57efbd6ac99400c030e0f2ad5d1a08f0da67c048062c38d3e03f878ed8
3
+ size 24925184
neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a25ba200015f53611a98122abf8350fdd8b1f4cd943d5b7dcc941bd97ebae3
3
+ size 747948
neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0aa4829b40ce02e95358d17fd1ff5ec87af3521029e6516f806ae044994616
3
+ size 10589184
neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4124d8e90956aa8e221abb385545c89840308da6811d9e17c8d0277d0fead877
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96128cb1e469e0a6d934f6783a3dc67951d6ddf2f732153b259a0b6704b3c4c1
3
+ size 9309184
neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f408ef59ea5fd80364b47d0a855c5020e7608bf19a2395a26a69e17ff05e7a2d
3
+ size 756689
neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f903f29917106c9a3587eae4cabc2a1e9b8ac32444f1ed674ed9c235946106de
3
+ size 8735744