Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
550
dacorvo HF Staff commited on
Commit
779ec7d
·
verified ·
1 Parent(s): 5e828c9

Synchronizing local compiler cache.

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +344 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/5eef7da50a217db5b302.json +97 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/3292185f0123466a93a2.json +79 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b60dca7d7a9c53810fe0.json +79 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b9b0c081795fa9e33ca6.json +79 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/082c855afd5bbe38fea8.json +54 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/19ebb6a6a5ec909e86f1.json +55 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/1e1cab9afee16970464a.json +55 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/2420b2b633bc1e938403.json +54 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/3585a8b7eec15ef74cc9.json +55 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/4d038e1c09d623b63731.json +55 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/59c92a651b8b40190b9d.json +54 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/707d5fc3c98b3c204500.json +54 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/8829976eff976b676195.json +54 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/903f2ac3444c8203b948.json +54 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/9b69ad26e6071c069631.json +55 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/aa7706c37f42f9b0efa0.json +54 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/b5b638607d26526724c7.json +54 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/ce96b3b9bef1f6cf0d93.json +55 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/cf3a4b3035690a565ab1.json +55 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/d2da3177c42e88297899.json +55 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/e59dd1535caa6a29b4cc.json +54 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/beit/hf-internal-testing/tiny-random-BeitForImageClassification/7b8399664c54026a03ff.json +90 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/beit/hf-internal-testing/tiny-random-BeitForImageClassification/8eea34f80bdd528f4c47.json +90 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/Jingya/tiny-random-bert-remote-code/601076bf2990d898404b.json +52 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/fxmarty/tiny-bert-sst2-distilled-subfolder/d7d576d06e1491d72e5a.json +61 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/07d9dac237105afed7b4.json +52 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/0d7dca7e1b02d11fa30b.json +52 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/22ce2cce0b08d134021c.json +53 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/28bcefedc9caadd676ab.json +53 -0
  31. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/3908bf519c210b434176.json +53 -0
  32. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/5ead9d705b13f37e716b.json +52 -0
  33. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/80c925bab2fcc5749b91.json +53 -0
  34. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/92f51980d46489605055.json +52 -0
  35. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/aeebf3f56cf9d0ed0250.json +52 -0
  36. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/cfb94bae5629e275593f.json +53 -0
  37. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e050716b5de372871d73.json +52 -0
  38. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e0768f223c51e12fd868.json +52 -0
  39. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e2594a1f187f452902f7.json +52 -0
  40. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e4834fd951418b796374.json +53 -0
  41. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e7e71e6beffbf701391b.json +53 -0
  42. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/ea81a963f6aa67da9f09.json +53 -0
  43. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/ef32dca934503ba9400c.json +52 -0
  44. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/f15944a91bf873bc4059.json +52 -0
  45. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/sentence-transformers/all-MiniLM-L6-v2/b571d0d9ac9ad084fa8c.json +54 -0
  46. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/sentence-transformers/all-MiniLM-L6-v2/f99a0822ae493faf0bb5.json +54 -0
  47. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/16650c04744503a0af47.json +52 -0
  48. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/3d5fe21de242b8b602d5.json +52 -0
  49. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/4b4a4fbbe9d668bcf61e.json +52 -0
  50. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/5bca725791b646775427.json +53 -0
.gitattributes CHANGED
@@ -10270,3 +10270,347 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_057bc784fc164fb34d3e+ed72d204/model.neff f
10270
  neuronxcc-2.20.9961.0+0acef03a/MODULE_de733c6f96020a1e5f56+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10271
  neuronxcc-2.20.9961.0+0acef03a/MODULE_de733c6f96020a1e5f56+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10272
  neuronxcc-2.20.9961.0+0acef03a/MODULE_e3031c3c114f7c905db7+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10270
  neuronxcc-2.20.9961.0+0acef03a/MODULE_de733c6f96020a1e5f56+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10271
  neuronxcc-2.20.9961.0+0acef03a/MODULE_de733c6f96020a1e5f56+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10272
  neuronxcc-2.20.9961.0+0acef03a/MODULE_e3031c3c114f7c905db7+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
10273
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0219e831452f3e9b80e6/model.neuron filter=lfs diff=lfs merge=lfs -text
10274
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_021be40fb5716d1066d1/model.neuron filter=lfs diff=lfs merge=lfs -text
10275
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_02c51eae95f4097f74e7/model.neuron filter=lfs diff=lfs merge=lfs -text
10276
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_07d9dac237105afed7b4/model.neuron filter=lfs diff=lfs merge=lfs -text
10277
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_082c855afd5bbe38fea8/model.neuron filter=lfs diff=lfs merge=lfs -text
10278
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0994f3d43a554bcbbcd7/model.neuron filter=lfs diff=lfs merge=lfs -text
10279
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0ad6e67d0b4363af0472/model.neuron filter=lfs diff=lfs merge=lfs -text
10280
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0af77bd813eb760ae10d/model.neuron filter=lfs diff=lfs merge=lfs -text
10281
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b0b6686a4841c281f89/model.neuron filter=lfs diff=lfs merge=lfs -text
10282
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b384d0739d57659345e/model.neuron filter=lfs diff=lfs merge=lfs -text
10283
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bfe6d17355fd2f0836f/model.neuron filter=lfs diff=lfs merge=lfs -text
10284
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0ca055684d61c552e3ec/model.neuron filter=lfs diff=lfs merge=lfs -text
10285
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0ca23862a0ff1499156f/model.neuron filter=lfs diff=lfs merge=lfs -text
10286
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0d7dca7e1b02d11fa30b/model.neuron filter=lfs diff=lfs merge=lfs -text
10287
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0e02d4795b77fba80c35/model.neuron filter=lfs diff=lfs merge=lfs -text
10288
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f556b899de48f28b455/model.neuron filter=lfs diff=lfs merge=lfs -text
10289
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0fdfb4247e7d07ebbad0/model.neuron filter=lfs diff=lfs merge=lfs -text
10290
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_101f045ec3ef38dff069/model.neuron filter=lfs diff=lfs merge=lfs -text
10291
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_11228616321528259762+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10292
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1179fb416e242252b8b1/model.neuron filter=lfs diff=lfs merge=lfs -text
10293
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_117dcaf2b5ba5b392c51/model.neuron filter=lfs diff=lfs merge=lfs -text
10294
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_11d26d78110e3ea447dd/model.neuron filter=lfs diff=lfs merge=lfs -text
10295
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_12273156641748218648+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10296
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1227467f6a1477aec333/model.neuron filter=lfs diff=lfs merge=lfs -text
10297
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1355027528627e06e5cb/model.neuron filter=lfs diff=lfs merge=lfs -text
10298
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_136344c1e04a80fc9e83/model.neuron filter=lfs diff=lfs merge=lfs -text
10299
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_14069605881026998085+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10300
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_14160024224657763603+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10301
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_14829227305888857035+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10302
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_148a07ab282c4e1a2a0e/model.neuron filter=lfs diff=lfs merge=lfs -text
10303
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_15025462673285903344+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10304
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_15f7e443873c3474a6aa/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10305
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_15f7e443873c3474a6aa/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10306
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_16650c04744503a0af47/model.neuron filter=lfs diff=lfs merge=lfs -text
10307
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_16839706381867715922+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10308
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_16b01b31bf5bb1c85c1d/model.neuron filter=lfs diff=lfs merge=lfs -text
10309
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_17327912813737302838+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10310
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_17419856824540332941+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10311
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_17641195202625304294+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10312
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_17711110885328520544+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10313
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_17855694184933887987+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10314
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d9b81ae20431d278e/model.neuron filter=lfs diff=lfs merge=lfs -text
10315
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_18d8cc6bf53b525ebb83/model.neuron filter=lfs diff=lfs merge=lfs -text
10316
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_19a9557944c3c798892c/model.neuron filter=lfs diff=lfs merge=lfs -text
10317
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_19ebb6a6a5ec909e86f1/model.neuron filter=lfs diff=lfs merge=lfs -text
10318
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ae5dec75b26da7fc293+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
10319
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1be47d7ec35995ba24e2/model.neuron filter=lfs diff=lfs merge=lfs -text
10320
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ccdb35db19ea6d46330/model.neuron filter=lfs diff=lfs merge=lfs -text
10321
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d4e0541af5c102c02ad/model.neuron filter=lfs diff=lfs merge=lfs -text
10322
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e1cab9afee16970464a/model.neuron filter=lfs diff=lfs merge=lfs -text
10323
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1f71844521461b69a9a1/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10324
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1f71844521461b69a9a1/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10325
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1f71844521461b69a9a1/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10326
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1f71844521461b69a9a1/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10327
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1f997b4c07c5b98b2872/model.neuron filter=lfs diff=lfs merge=lfs -text
10328
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2011979c1c7685c0c1e8/model.neuron filter=lfs diff=lfs merge=lfs -text
10329
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_22ac4beaed8c828e276d/model.neuron filter=lfs diff=lfs merge=lfs -text
10330
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_22ce2cce0b08d134021c/model.neuron filter=lfs diff=lfs merge=lfs -text
10331
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2420b2b633bc1e938403/model.neuron filter=lfs diff=lfs merge=lfs -text
10332
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2518ad68ffda816de14c+a74130ed/model.neff filter=lfs diff=lfs merge=lfs -text
10333
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2518ad68ffda816de14c+a74130ed/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10334
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_27494e54568e0f4aef97/model.neuron filter=lfs diff=lfs merge=lfs -text
10335
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_28bcefedc9caadd676ab/model.neuron filter=lfs diff=lfs merge=lfs -text
10336
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2994655886375ea65794/model.neuron filter=lfs diff=lfs merge=lfs -text
10337
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bfc916223b281bde6c9/model.neuron filter=lfs diff=lfs merge=lfs -text
10338
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3447cbfc1aa2c980e4/model.neuron filter=lfs diff=lfs merge=lfs -text
10339
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d941194111edd1cc349/model.neuron filter=lfs diff=lfs merge=lfs -text
10340
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2ec978f7548ba514cc92/model.neuron filter=lfs diff=lfs merge=lfs -text
10341
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2eeccd3fb290738b486c/model.neuron filter=lfs diff=lfs merge=lfs -text
10342
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_30709c9a1366cc22f381/model.neuron filter=lfs diff=lfs merge=lfs -text
10343
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3091516cc256301854d5/model.neuron filter=lfs diff=lfs merge=lfs -text
10344
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3164ef3b6e4540774d38/model.neuron filter=lfs diff=lfs merge=lfs -text
10345
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3262637bc52e95809853+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
10346
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_33c68608ff1365e11b4b/model.neuron filter=lfs diff=lfs merge=lfs -text
10347
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_35240b83eadb946e8397/model.neuron filter=lfs diff=lfs merge=lfs -text
10348
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3585a8b7eec15ef74cc9/model.neuron filter=lfs diff=lfs merge=lfs -text
10349
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3666724308aaa469662b/model.neuron filter=lfs diff=lfs merge=lfs -text
10350
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_37fb28b99dfea65dc5fd/model.neuron filter=lfs diff=lfs merge=lfs -text
10351
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_38fe3c7c7cf144065eac/model.neuron filter=lfs diff=lfs merge=lfs -text
10352
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3908bf519c210b434176/model.neuron filter=lfs diff=lfs merge=lfs -text
10353
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_39152d050ca1aafdbcb7/model.neuron filter=lfs diff=lfs merge=lfs -text
10354
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3bf2eb59f27536b63a45/model.neuron filter=lfs diff=lfs merge=lfs -text
10355
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3d5fe21de242b8b602d5/model.neuron filter=lfs diff=lfs merge=lfs -text
10356
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_3f7a39fcaca1f42af1d6/model.neuron filter=lfs diff=lfs merge=lfs -text
10357
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4067177570182b1343d2/model.neuron filter=lfs diff=lfs merge=lfs -text
10358
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4148dd3c4e0957c59aec/model.neuron filter=lfs diff=lfs merge=lfs -text
10359
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4375062474730619889+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10360
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_44670f0e856e93e13945/model.neuron filter=lfs diff=lfs merge=lfs -text
10361
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_45c7246705c9e6fab659/model.neuron filter=lfs diff=lfs merge=lfs -text
10362
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_466672b98b30e850228e/model.neuron filter=lfs diff=lfs merge=lfs -text
10363
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_467e3986218b1c421e16/model.neuron filter=lfs diff=lfs merge=lfs -text
10364
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4696932584f9d8f704d5/model.neuron filter=lfs diff=lfs merge=lfs -text
10365
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4750006367237009755+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10366
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_484d55fa9705364e6d6c/model.neuron filter=lfs diff=lfs merge=lfs -text
10367
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_491a208ef81533ee4361/model.neuron filter=lfs diff=lfs merge=lfs -text
10368
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4974b909ef52ed6985aa/model.neuron filter=lfs diff=lfs merge=lfs -text
10369
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4b4a4fbbe9d668bcf61e/model.neuron filter=lfs diff=lfs merge=lfs -text
10370
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4b5db21c35dab98379c0/model.neuron filter=lfs diff=lfs merge=lfs -text
10371
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4bf35dcb438eff118841/model.neuron filter=lfs diff=lfs merge=lfs -text
10372
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4d038e1c09d623b63731/model.neuron filter=lfs diff=lfs merge=lfs -text
10373
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4d2fe63b7ea76c7ef876+a74130ed/model.neff filter=lfs diff=lfs merge=lfs -text
10374
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4d2fe63b7ea76c7ef876+a74130ed/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10375
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4e4ef27b3302beb416e2+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
10376
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_50466361a10e0beb2743/model.neuron filter=lfs diff=lfs merge=lfs -text
10377
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_50881c62b5e180d29b73/model.neuron filter=lfs diff=lfs merge=lfs -text
10378
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_50dd1eff58edae4890c4/model.neuron filter=lfs diff=lfs merge=lfs -text
10379
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_52ac96dddc861615c14b/model.neuron filter=lfs diff=lfs merge=lfs -text
10380
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_530b46c2c544923d9ae4/model.neuron filter=lfs diff=lfs merge=lfs -text
10381
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5321652960071550735+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10382
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_54999f3651eabb911710/model.neuron filter=lfs diff=lfs merge=lfs -text
10383
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_565ec63172e78bb6a459/model.neuron filter=lfs diff=lfs merge=lfs -text
10384
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_566b362576597dc93bf0/model.neuron filter=lfs diff=lfs merge=lfs -text
10385
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_56fb08782842e65d4478/model.neuron filter=lfs diff=lfs merge=lfs -text
10386
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_56fb7ca25c9741358f35/model.neuron filter=lfs diff=lfs merge=lfs -text
10387
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_57575a85181cb2c0c6ce/model.neuron filter=lfs diff=lfs merge=lfs -text
10388
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_59287e3a63d75be1484e/model.neuron filter=lfs diff=lfs merge=lfs -text
10389
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_59c92a651b8b40190b9d/model.neuron filter=lfs diff=lfs merge=lfs -text
10390
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5bca725791b646775427/model.neuron filter=lfs diff=lfs merge=lfs -text
10391
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5cfaeab2b13c776d07bb/model.neuron filter=lfs diff=lfs merge=lfs -text
10392
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d5dadc2c2138bf8ab44/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10393
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d5dadc2c2138bf8ab44/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10394
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dba74ecad23c5836b41/model.neuron filter=lfs diff=lfs merge=lfs -text
10395
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5de28d74475c2e525475/model.neuron filter=lfs diff=lfs merge=lfs -text
10396
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5e0f1f4e96fb7f38115d/model.neuron filter=lfs diff=lfs merge=lfs -text
10397
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ead9d705b13f37e716b/model.neuron filter=lfs diff=lfs merge=lfs -text
10398
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ee5e7496586a5b158cd/model.neuron filter=lfs diff=lfs merge=lfs -text
10399
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fb0198cf9dd4a2e93ea/model.neuron filter=lfs diff=lfs merge=lfs -text
10400
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fc297836c63bcff7ed3/model.neuron filter=lfs diff=lfs merge=lfs -text
10401
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_601076bf2990d898404b/model.neuron filter=lfs diff=lfs merge=lfs -text
10402
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_602b46624db97cda3fee/model.neuron filter=lfs diff=lfs merge=lfs -text
10403
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6081e29d0b26014e391f/model.neuron filter=lfs diff=lfs merge=lfs -text
10404
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_61774b9874fadd5b1723/model.neuron filter=lfs diff=lfs merge=lfs -text
10405
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_61a96b508e7be967c0c7+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
10406
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_61a96b508e7be967c0c7+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10407
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_62c0826140d6564782c3/model.neuron filter=lfs diff=lfs merge=lfs -text
10408
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6356dda8884e943ca1eb/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10409
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6356dda8884e943ca1eb/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
10410
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6356dda8884e943ca1eb/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10411
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6356dda8884e943ca1eb/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10412
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6356dda8884e943ca1eb/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10413
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_639b34a908c080e3d3e9/model.neuron filter=lfs diff=lfs merge=lfs -text
10414
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_63b1a6be8b23f66fef00/model.neuron filter=lfs diff=lfs merge=lfs -text
10415
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_64383c5d9ccd5d74a246/model.neuron filter=lfs diff=lfs merge=lfs -text
10416
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_64a180bec331b8ec91ba/model.neuron filter=lfs diff=lfs merge=lfs -text
10417
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_655beeec84479afaaafe/model.neuron filter=lfs diff=lfs merge=lfs -text
10418
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_66be3aba74892f370b62/model.neuron filter=lfs diff=lfs merge=lfs -text
10419
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_68d42db5e52211fa0dc3/model.neuron filter=lfs diff=lfs merge=lfs -text
10420
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_68df0af504c21aa2b1ce/model.neuron filter=lfs diff=lfs merge=lfs -text
10421
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6903f75a616124fbbe62/model.neuron filter=lfs diff=lfs merge=lfs -text
10422
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_69748744deacc485a2da/model.neuron filter=lfs diff=lfs merge=lfs -text
10423
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a46f0468637fa1ceea4/model.neuron filter=lfs diff=lfs merge=lfs -text
10424
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b45e20838de2009119b/model.neuron filter=lfs diff=lfs merge=lfs -text
10425
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6cdfd3f8d054eaf72194/model.neuron filter=lfs diff=lfs merge=lfs -text
10426
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e06599623de7d47c750/model.neuron filter=lfs diff=lfs merge=lfs -text
10427
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec1ef9088ffe38a3d25/model.neuron filter=lfs diff=lfs merge=lfs -text
10428
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_707d5fc3c98b3c204500/model.neuron filter=lfs diff=lfs merge=lfs -text
10429
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_70a99404c72ad381de36/model.neuron filter=lfs diff=lfs merge=lfs -text
10430
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ae67fe6de015024b24+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
10431
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ae67fe6de015024b24+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10432
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_71d6f99f019cce5d2c56/model.neuron filter=lfs diff=lfs merge=lfs -text
10433
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7291119501971561507+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10434
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_72b1081c4393b26efe11/model.neuron filter=lfs diff=lfs merge=lfs -text
10435
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_733d8ce97f615c7406f6/model.neuron filter=lfs diff=lfs merge=lfs -text
10436
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_749c49190e3a9c9b1317/model.neuron filter=lfs diff=lfs merge=lfs -text
10437
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_74c4ec2a3829c1027457/model.neuron filter=lfs diff=lfs merge=lfs -text
10438
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_77e174f71c47d9f4d0b7/model.neuron filter=lfs diff=lfs merge=lfs -text
10439
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b1d8863929b4701df6d/model.neuron filter=lfs diff=lfs merge=lfs -text
10440
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b8399664c54026a03ff/model.neuron filter=lfs diff=lfs merge=lfs -text
10441
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7be6e0568963be54593a/model.neuron filter=lfs diff=lfs merge=lfs -text
10442
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7cc364920677c1ace017/model.neuron filter=lfs diff=lfs merge=lfs -text
10443
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7dd477985731dbce8cf8/model.neuron filter=lfs diff=lfs merge=lfs -text
10444
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7ec9c0b2b3c87c96c7d0/model.neuron filter=lfs diff=lfs merge=lfs -text
10445
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_80563bbcc3f75213156d/model.neuron filter=lfs diff=lfs merge=lfs -text
10446
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_80c925bab2fcc5749b91/model.neuron filter=lfs diff=lfs merge=lfs -text
10447
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8285b8316500e52286c9/model.neuron filter=lfs diff=lfs merge=lfs -text
10448
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8319eff5a8285defb5a3/model.neuron filter=lfs diff=lfs merge=lfs -text
10449
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_833bce8fd7e57021a525/model.neuron filter=lfs diff=lfs merge=lfs -text
10450
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83466d3415d7c423ad3a/model.neuron filter=lfs diff=lfs merge=lfs -text
10451
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83b76f3670fb9dd6d79d/model.neuron filter=lfs diff=lfs merge=lfs -text
10452
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8417307499696621353+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
10453
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_855c66679f1728d4b0b9/model.neuron filter=lfs diff=lfs merge=lfs -text
10454
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_876a3fac78c9e7d8d969/model.neuron filter=lfs diff=lfs merge=lfs -text
10455
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_87b36020196a848d8295/model.neuron filter=lfs diff=lfs merge=lfs -text
10456
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_87eb7ec28b9b01a3f8de/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10457
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_87eb7ec28b9b01a3f8de/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10458
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_87eb7ec28b9b01a3f8de/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10459
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_87eb7ec28b9b01a3f8de/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10460
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8829976eff976b676195/model.neuron filter=lfs diff=lfs merge=lfs -text
10461
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_88abbb6c39ef61b204e1/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10462
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_88abbb6c39ef61b204e1/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10463
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_896e2cb6bda1ecefc195/model.neuron filter=lfs diff=lfs merge=lfs -text
10464
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_89c332555d9bb1164bb3+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
10465
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8afa7462593888c1ace0/model.neuron filter=lfs diff=lfs merge=lfs -text
10466
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8b1a6646a196796c979b/model.neuron filter=lfs diff=lfs merge=lfs -text
10467
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8eea34f80bdd528f4c47/model.neuron filter=lfs diff=lfs merge=lfs -text
10468
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9013e8baf47aa2490da7/model.neuron filter=lfs diff=lfs merge=lfs -text
10469
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_903f2ac3444c8203b948/model.neuron filter=lfs diff=lfs merge=lfs -text
10470
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_922088b97905a7fc46ca/model.neuron filter=lfs diff=lfs merge=lfs -text
10471
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9280fd71681625e0f026/model.neuron filter=lfs diff=lfs merge=lfs -text
10472
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_92b322085492cfc5743f/model.neuron filter=lfs diff=lfs merge=lfs -text
10473
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_92f51980d46489605055/model.neuron filter=lfs diff=lfs merge=lfs -text
10474
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_93fb6328ff6b4914fec7/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10475
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_93fb6328ff6b4914fec7/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
10476
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_93fb6328ff6b4914fec7/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10477
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_93fb6328ff6b4914fec7/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10478
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_93fb6328ff6b4914fec7/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10479
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_950e3bf7ec0e47e9d1f6/model.neuron filter=lfs diff=lfs merge=lfs -text
10480
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9584ca4279d47aa94f96/model.neuron filter=lfs diff=lfs merge=lfs -text
10481
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_96263cd071abd0bb8205/model.neuron filter=lfs diff=lfs merge=lfs -text
10482
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_96735d336b988c7ae46c/model.neuron filter=lfs diff=lfs merge=lfs -text
10483
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_96f2f0fe551f33210e73/model.neuron filter=lfs diff=lfs merge=lfs -text
10484
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_98afed8f23bccfa2bf93/model.neuron filter=lfs diff=lfs merge=lfs -text
10485
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_99a4d278a736dc55c4e1/model.neuron filter=lfs diff=lfs merge=lfs -text
10486
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_99bc626550f56c193835/model.neuron filter=lfs diff=lfs merge=lfs -text
10487
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a0e849430be2af050d7/model.neuron filter=lfs diff=lfs merge=lfs -text
10488
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a67f4255c65b566abfd/model.neuron filter=lfs diff=lfs merge=lfs -text
10489
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9b1e403c2901fc8169d9/model.neuron filter=lfs diff=lfs merge=lfs -text
10490
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9b69ad26e6071c069631/model.neuron filter=lfs diff=lfs merge=lfs -text
10491
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7952fae90c1f6f8fb4/model.neuron filter=lfs diff=lfs merge=lfs -text
10492
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9f5df17622d13f7aa0a1/model.neuron filter=lfs diff=lfs merge=lfs -text
10493
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9f6a8efd40fcd1be4ca9/model.neuron filter=lfs diff=lfs merge=lfs -text
10494
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1326d88e9b290f8e35a/controlnet_0/model.neuron filter=lfs diff=lfs merge=lfs -text
10495
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1326d88e9b290f8e35a/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10496
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1326d88e9b290f8e35a/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10497
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1326d88e9b290f8e35a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10498
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1326d88e9b290f8e35a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10499
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a456d73c225440c520af/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10500
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a456d73c225440c520af/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10501
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a456d73c225440c520af/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10502
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a456d73c225440c520af/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10503
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e434271f70307fe55a/model.neuron filter=lfs diff=lfs merge=lfs -text
10504
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a7dcaa4d6f7541916f6b/model.neuron filter=lfs diff=lfs merge=lfs -text
10505
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa7706c37f42f9b0efa0/model.neuron filter=lfs diff=lfs merge=lfs -text
10506
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab0ec5a632242310c520/model.neuron filter=lfs diff=lfs merge=lfs -text
10507
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac82cc5cd27456228f9b/model.neuron filter=lfs diff=lfs merge=lfs -text
10508
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad9de1959357baf1be93/model.neuron filter=lfs diff=lfs merge=lfs -text
10509
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeebf3f56cf9d0ed0250/model.neuron filter=lfs diff=lfs merge=lfs -text
10510
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_af36677e1d281b7581b7/model.neuron filter=lfs diff=lfs merge=lfs -text
10511
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b26cf211d0154814b6de/model.neuron filter=lfs diff=lfs merge=lfs -text
10512
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b2a5715c8de1d06e02d1/model.neuron filter=lfs diff=lfs merge=lfs -text
10513
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b45d43ae8e345b80b8b6/model.neuron filter=lfs diff=lfs merge=lfs -text
10514
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b46c903d70fcbd8dde04/model.neuron filter=lfs diff=lfs merge=lfs -text
10515
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b571d0d9ac9ad084fa8c/model.neuron filter=lfs diff=lfs merge=lfs -text
10516
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b5b638607d26526724c7/model.neuron filter=lfs diff=lfs merge=lfs -text
10517
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b6abe5e7902b7d92c00b/model.neuron filter=lfs diff=lfs merge=lfs -text
10518
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b825412615cae3305380/model.neuron filter=lfs diff=lfs merge=lfs -text
10519
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/controlnet_0/model.neuron filter=lfs diff=lfs merge=lfs -text
10520
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/controlnet_1/model.neuron filter=lfs diff=lfs merge=lfs -text
10521
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10522
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10523
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10524
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b83eb9efb666a7597fa6/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10525
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba276d9e084c36d4d299/model.neuron filter=lfs diff=lfs merge=lfs -text
10526
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb5b129941b54904675f/model.neuron filter=lfs diff=lfs merge=lfs -text
10527
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc33d8c25a64bc49fa25/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10528
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc33d8c25a64bc49fa25/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
10529
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc33d8c25a64bc49fa25/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10530
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc33d8c25a64bc49fa25/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10531
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc33d8c25a64bc49fa25/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10532
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc7d63ab74772beafa77/model.neuron filter=lfs diff=lfs merge=lfs -text
10533
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bd8a7636ac96599afce0/model.neuron filter=lfs diff=lfs merge=lfs -text
10534
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf898d9815ecfc28a3c4/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10535
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf898d9815ecfc28a3c4/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10536
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c121d453d2dce97dc9f2/model.neuron filter=lfs diff=lfs merge=lfs -text
10537
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c1a7e229a1e0089bc100/model.neuron filter=lfs diff=lfs merge=lfs -text
10538
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c3dac669c643d4e0b641/model.neuron filter=lfs diff=lfs merge=lfs -text
10539
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6a6313df00b13f0bc20/model.neuron filter=lfs diff=lfs merge=lfs -text
10540
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c76ea064827fb5ffaf3a/model.neuron filter=lfs diff=lfs merge=lfs -text
10541
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7711f055c4601678bfc/model.neuron filter=lfs diff=lfs merge=lfs -text
10542
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c845c7c1978a7f0fc5bc+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
10543
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c845c7c1978a7f0fc5bc+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10544
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cd2b22a4d8bd6ff87e79/model.neuron filter=lfs diff=lfs merge=lfs -text
10545
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ce96b3b9bef1f6cf0d93/model.neuron filter=lfs diff=lfs merge=lfs -text
10546
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cf3a4b3035690a565ab1/model.neuron filter=lfs diff=lfs merge=lfs -text
10547
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cfb94bae5629e275593f/model.neuron filter=lfs diff=lfs merge=lfs -text
10548
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cfbfacea58d61c7302ac/model.neuron filter=lfs diff=lfs merge=lfs -text
10549
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d0207458a6f6fb104830/model.neuron filter=lfs diff=lfs merge=lfs -text
10550
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d0dd0aeeae66ba529c6f/model.neuron filter=lfs diff=lfs merge=lfs -text
10551
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d2c282677041876b494e/model.neuron filter=lfs diff=lfs merge=lfs -text
10552
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d2da3177c42e88297899/model.neuron filter=lfs diff=lfs merge=lfs -text
10553
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d327dc6d21691f2390f2/model.neuron filter=lfs diff=lfs merge=lfs -text
10554
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9e3a3693c0097041a/model.neuron filter=lfs diff=lfs merge=lfs -text
10555
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d4527b583703e675299f/model.neuron filter=lfs diff=lfs merge=lfs -text
10556
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d5fb9a76d0fdc62db217/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10557
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d5fb9a76d0fdc62db217/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10558
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d5fb9a76d0fdc62db217/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10559
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d5fb9a76d0fdc62db217/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10560
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d63d38954db56a481479/model.neuron filter=lfs diff=lfs merge=lfs -text
10561
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d752631e2f1bc8b5bd5c/model.neuron filter=lfs diff=lfs merge=lfs -text
10562
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d780aaa6e4cc8ef4073b/model.neuron filter=lfs diff=lfs merge=lfs -text
10563
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7d576d06e1491d72e5a/model.neuron filter=lfs diff=lfs merge=lfs -text
10564
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d83e395611ddc3a29d9f/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10565
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d83e395611ddc3a29d9f/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10566
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_db7feb9a8e6a89d9b5cc/model.neuron filter=lfs diff=lfs merge=lfs -text
10567
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_dbf38214a01c36374929/model.neuron filter=lfs diff=lfs merge=lfs -text
10568
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc19e38388ce4a13824f/model.neuron filter=lfs diff=lfs merge=lfs -text
10569
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcfeb3310672a794fe59/model.neuron filter=lfs diff=lfs merge=lfs -text
10570
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_dec4d4d1adf057ba26a6/model.neuron filter=lfs diff=lfs merge=lfs -text
10571
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e00b8a80c7b4565a38b9/model.neuron filter=lfs diff=lfs merge=lfs -text
10572
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e01d4f3ed05b3b779179/model.neuron filter=lfs diff=lfs merge=lfs -text
10573
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e050716b5de372871d73/model.neuron filter=lfs diff=lfs merge=lfs -text
10574
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e0768f223c51e12fd868/model.neuron filter=lfs diff=lfs merge=lfs -text
10575
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e0d110db2ae6fd6f9a18/model.neuron filter=lfs diff=lfs merge=lfs -text
10576
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e0e485d1effe77c0355a/model.neuron filter=lfs diff=lfs merge=lfs -text
10577
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e207d10cd73986f34774/model.neuron filter=lfs diff=lfs merge=lfs -text
10578
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e2594a1f187f452902f7/model.neuron filter=lfs diff=lfs merge=lfs -text
10579
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3343136a71050139f62/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10580
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3343136a71050139f62/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
10581
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3343136a71050139f62/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
10582
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3343136a71050139f62/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10583
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3343136a71050139f62/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10584
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4834fd951418b796374/model.neuron filter=lfs diff=lfs merge=lfs -text
10585
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e57cbde649dde732937d/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10586
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e57cbde649dde732937d/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10587
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e59dd1535caa6a29b4cc/model.neuron filter=lfs diff=lfs merge=lfs -text
10588
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e5c893a9ead6645e9326/model.neuron filter=lfs diff=lfs merge=lfs -text
10589
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e7d6a1ed3ce052d450ca/model.neuron filter=lfs diff=lfs merge=lfs -text
10590
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e7e71e6beffbf701391b/model.neuron filter=lfs diff=lfs merge=lfs -text
10591
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea65e810b73a07c4f93e/model.neuron filter=lfs diff=lfs merge=lfs -text
10592
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea81a963f6aa67da9f09/model.neuron filter=lfs diff=lfs merge=lfs -text
10593
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_eaa04c5b1a458bb8ede4/model.neuron filter=lfs diff=lfs merge=lfs -text
10594
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_eaffcb1bcf2a2ba5568c/model.neuron filter=lfs diff=lfs merge=lfs -text
10595
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ebdd3f238f484caa6f2b/model.neuron filter=lfs diff=lfs merge=lfs -text
10596
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed32d4174c8c48368338/model.neuron filter=lfs diff=lfs merge=lfs -text
10597
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef32dca934503ba9400c/model.neuron filter=lfs diff=lfs merge=lfs -text
10598
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f0f76b9ba98b72bdf648/model.neuron filter=lfs diff=lfs merge=lfs -text
10599
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f15944a91bf873bc4059/model.neuron filter=lfs diff=lfs merge=lfs -text
10600
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f1ec63e05f9ea876842c/model.neuron filter=lfs diff=lfs merge=lfs -text
10601
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f2764d531dd4d92fcf44/model.neuron filter=lfs diff=lfs merge=lfs -text
10602
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f2fb67dde0ac51075166/model.neuron filter=lfs diff=lfs merge=lfs -text
10603
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3e9a9a693c44ea917dc/model.neuron filter=lfs diff=lfs merge=lfs -text
10604
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f441d043990635e01090/model.neuron filter=lfs diff=lfs merge=lfs -text
10605
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f58c375fdf2f49018e38/model.neuron filter=lfs diff=lfs merge=lfs -text
10606
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f59412f8a600e9a71fb8/model.neuron filter=lfs diff=lfs merge=lfs -text
10607
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f73c821d92438436ad6c/model.neuron filter=lfs diff=lfs merge=lfs -text
10608
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8697b18674e9f438a96/model.neuron filter=lfs diff=lfs merge=lfs -text
10609
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8990edfbb4deaf97027/model.neuron filter=lfs diff=lfs merge=lfs -text
10610
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f99a0822ae493faf0bb5/model.neuron filter=lfs diff=lfs merge=lfs -text
10611
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_fa6da73026ca7a0eb10f/model.neuron filter=lfs diff=lfs merge=lfs -text
10612
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_fba7e5f3d8634f923189/model.neuron filter=lfs diff=lfs merge=lfs -text
10613
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_fd402f1583fe91543618/model.neuron filter=lfs diff=lfs merge=lfs -text
10614
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe61ce3dd9af75901342/model.neuron filter=lfs diff=lfs merge=lfs -text
10615
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ff3a95a3a80afa64563d/model.neuron filter=lfs diff=lfs merge=lfs -text
10616
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ffe8abf61d5a2a0a2b8e/model.neuron filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/5eef7da50a217db5b302.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "async_mode": false,
45
+ "attn_kernel_enabled": false,
46
+ "batch_size": 1,
47
+ "capacity_factor": null,
48
+ "cc_pipeline_tiling_factor": 2,
49
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
50
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
51
+ "continuous_batching": false,
52
+ "enable_bucketing": false,
53
+ "ep_degree": 1,
54
+ "flash_decoding_enabled": false,
55
+ "fused_qkv": false,
56
+ "glu_mlp": true,
57
+ "is_chunked_prefill": false,
58
+ "local_ranks_size": 2,
59
+ "logical_nc_config": 1,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 128,
62
+ "max_topk": 256,
63
+ "mlp_kernel_enabled": false,
64
+ "mlp_kernel_fuse_residual_add": false,
65
+ "n_active_tokens": 128,
66
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
67
+ "num_cores_per_group": 1,
68
+ "on_device_sampling": true,
69
+ "optimum_neuron_version": "0.3.1.dev0",
70
+ "output_logits": false,
71
+ "padding_side": "right",
72
+ "pp_degree": 1,
73
+ "qk_layernorm": false,
74
+ "qkv_kernel_enabled": false,
75
+ "rpl_reduce_dtype": "bfloat16",
76
+ "sequence_length": 128,
77
+ "sequence_parallel_enabled": false,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": null,
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2,
83
+ "vocab_parallel": false
84
+ },
85
+ "num_attention_heads": 14,
86
+ "num_hidden_layers": 24,
87
+ "num_key_value_heads": 2,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_scaling": null,
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": null,
92
+ "tie_word_embeddings": true,
93
+ "use_cache": true,
94
+ "use_mrope": false,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 151936
97
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/3292185f0123466a93a2.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention"
16
+ ],
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 1,
19
+ "model_type": "qwen2",
20
+ "neuron": {
21
+ "_serialized_key": "NxDNeuronConfig",
22
+ "async_mode": false,
23
+ "attn_kernel_enabled": false,
24
+ "batch_size": 2,
25
+ "capacity_factor": null,
26
+ "cc_pipeline_tiling_factor": 2,
27
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
28
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
29
+ "continuous_batching": true,
30
+ "enable_bucketing": false,
31
+ "ep_degree": 1,
32
+ "flash_decoding_enabled": false,
33
+ "fused_qkv": false,
34
+ "glu_mlp": true,
35
+ "is_chunked_prefill": false,
36
+ "local_ranks_size": 2,
37
+ "logical_nc_config": 1,
38
+ "max_batch_size": 2,
39
+ "max_context_length": 100,
40
+ "max_topk": 256,
41
+ "mlp_kernel_enabled": false,
42
+ "mlp_kernel_fuse_residual_add": false,
43
+ "n_active_tokens": 100,
44
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
45
+ "num_cores_per_group": 1,
46
+ "on_device_sampling": false,
47
+ "optimum_neuron_version": "0.3.1.dev0",
48
+ "output_logits": false,
49
+ "padding_side": "right",
50
+ "pp_degree": 1,
51
+ "qk_layernorm": false,
52
+ "qkv_kernel_enabled": false,
53
+ "rpl_reduce_dtype": "float16",
54
+ "sequence_length": 100,
55
+ "sequence_parallel_enabled": false,
56
+ "speculation_length": 0,
57
+ "start_rank_id": 0,
58
+ "target": null,
59
+ "torch_dtype": "float16",
60
+ "tp_degree": 2,
61
+ "vocab_parallel": false
62
+ },
63
+ "num_attention_heads": 4,
64
+ "num_hidden_layers": 2,
65
+ "num_key_value_heads": 2,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_scaling": {
68
+ "factor": 4.0,
69
+ "original_max_position_embeddings": 32768,
70
+ "rope_type": "yarn",
71
+ "type": "yarn"
72
+ },
73
+ "rope_theta": 1000000.0,
74
+ "sliding_window": null,
75
+ "tie_word_embeddings": false,
76
+ "use_cache": true,
77
+ "use_sliding_window": false,
78
+ "vocab_size": 152064
79
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b60dca7d7a9c53810fe0.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention"
16
+ ],
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 1,
19
+ "model_type": "qwen2",
20
+ "neuron": {
21
+ "_serialized_key": "NxDNeuronConfig",
22
+ "async_mode": false,
23
+ "attn_kernel_enabled": false,
24
+ "batch_size": 1,
25
+ "capacity_factor": null,
26
+ "cc_pipeline_tiling_factor": 2,
27
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
28
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
29
+ "continuous_batching": false,
30
+ "enable_bucketing": false,
31
+ "ep_degree": 1,
32
+ "flash_decoding_enabled": false,
33
+ "fused_qkv": false,
34
+ "glu_mlp": true,
35
+ "is_chunked_prefill": false,
36
+ "local_ranks_size": 2,
37
+ "logical_nc_config": 1,
38
+ "max_batch_size": 1,
39
+ "max_context_length": 100,
40
+ "max_topk": 256,
41
+ "mlp_kernel_enabled": false,
42
+ "mlp_kernel_fuse_residual_add": false,
43
+ "n_active_tokens": 100,
44
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
45
+ "num_cores_per_group": 1,
46
+ "on_device_sampling": true,
47
+ "optimum_neuron_version": "0.3.1.dev0",
48
+ "output_logits": false,
49
+ "padding_side": "right",
50
+ "pp_degree": 1,
51
+ "qk_layernorm": false,
52
+ "qkv_kernel_enabled": false,
53
+ "rpl_reduce_dtype": "float16",
54
+ "sequence_length": 100,
55
+ "sequence_parallel_enabled": false,
56
+ "speculation_length": 0,
57
+ "start_rank_id": 0,
58
+ "target": null,
59
+ "torch_dtype": "float16",
60
+ "tp_degree": 2,
61
+ "vocab_parallel": false
62
+ },
63
+ "num_attention_heads": 4,
64
+ "num_hidden_layers": 2,
65
+ "num_key_value_heads": 2,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_scaling": {
68
+ "factor": 4.0,
69
+ "original_max_position_embeddings": 32768,
70
+ "rope_type": "yarn",
71
+ "type": "yarn"
72
+ },
73
+ "rope_theta": 1000000.0,
74
+ "sliding_window": null,
75
+ "tie_word_embeddings": false,
76
+ "use_cache": true,
77
+ "use_sliding_window": false,
78
+ "vocab_size": 152064
79
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b9b0c081795fa9e33ca6.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention"
16
+ ],
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 1,
19
+ "model_type": "qwen2",
20
+ "neuron": {
21
+ "_serialized_key": "NxDNeuronConfig",
22
+ "async_mode": false,
23
+ "attn_kernel_enabled": false,
24
+ "batch_size": 1,
25
+ "capacity_factor": null,
26
+ "cc_pipeline_tiling_factor": 2,
27
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
28
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
29
+ "continuous_batching": false,
30
+ "enable_bucketing": false,
31
+ "ep_degree": 1,
32
+ "flash_decoding_enabled": false,
33
+ "fused_qkv": false,
34
+ "glu_mlp": true,
35
+ "is_chunked_prefill": false,
36
+ "local_ranks_size": 2,
37
+ "logical_nc_config": 1,
38
+ "max_batch_size": 1,
39
+ "max_context_length": 100,
40
+ "max_topk": 256,
41
+ "mlp_kernel_enabled": false,
42
+ "mlp_kernel_fuse_residual_add": false,
43
+ "n_active_tokens": 100,
44
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
45
+ "num_cores_per_group": 1,
46
+ "on_device_sampling": true,
47
+ "optimum_neuron_version": "0.3.1.dev0",
48
+ "output_logits": false,
49
+ "padding_side": "right",
50
+ "pp_degree": 1,
51
+ "qk_layernorm": false,
52
+ "qkv_kernel_enabled": false,
53
+ "rpl_reduce_dtype": "bfloat16",
54
+ "sequence_length": 100,
55
+ "sequence_parallel_enabled": false,
56
+ "speculation_length": 0,
57
+ "start_rank_id": 0,
58
+ "target": null,
59
+ "torch_dtype": "bfloat16",
60
+ "tp_degree": 2,
61
+ "vocab_parallel": false
62
+ },
63
+ "num_attention_heads": 4,
64
+ "num_hidden_layers": 2,
65
+ "num_key_value_heads": 2,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_scaling": {
68
+ "factor": 4.0,
69
+ "original_max_position_embeddings": 32768,
70
+ "rope_type": "yarn",
71
+ "type": "yarn"
72
+ },
73
+ "rope_theta": 1000000.0,
74
+ "sliding_window": null,
75
+ "tie_word_embeddings": false,
76
+ "use_cache": true,
77
+ "use_sliding_window": false,
78
+ "vocab_size": 152064
79
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/082c855afd5bbe38fea8.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 128,
45
+ "task": "fill-mask",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/19ebb6a6a5ec909e86f1.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "last_hidden_state",
42
+ "pooler_output"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 32,
46
+ "task": "feature-extraction",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/1e1cab9afee16970464a.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "start_logits",
42
+ "end_logits"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 32,
46
+ "task": "question-answering",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/2420b2b633bc1e938403.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "text-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/3585a8b7eec15ef74cc9.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "multiple-choice",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_num_choices": 4,
45
+ "static_sequence_length": 128,
46
+ "task": "multiple-choice",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/4d038e1c09d623b63731.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "last_hidden_state",
42
+ "pooler_output"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 128,
46
+ "task": "feature-extraction",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/59c92a651b8b40190b9d.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "token-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/707d5fc3c98b3c204500.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "fill-mask",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/8829976eff976b676195.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 128,
45
+ "task": "token-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/903f2ac3444c8203b948.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "fill-mask",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/9b69ad26e6071c069631.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "start_logits",
42
+ "end_logits"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 128,
46
+ "task": "question-answering",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/aa7706c37f42f9b0efa0.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "token-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/b5b638607d26526724c7.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 128,
45
+ "task": "text-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/ce96b3b9bef1f6cf0d93.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "start_logits",
42
+ "end_logits"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 32,
46
+ "task": "question-answering",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/cf3a4b3035690a565ab1.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "last_hidden_state",
42
+ "pooler_output"
43
+ ],
44
+ "static_batch_size": 1,
45
+ "static_sequence_length": 32,
46
+ "task": "feature-extraction",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/d2da3177c42e88297899.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "multiple-choice",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_num_choices": 4,
45
+ "static_sequence_length": 128,
46
+ "task": "multiple-choice",
47
+ "tensor_parallel_size": 1
48
+ },
49
+ "num_attention_heads": 6,
50
+ "num_hidden_groups": 6,
51
+ "num_hidden_layers": 6,
52
+ "position_embedding_type": "absolute",
53
+ "type_vocab_size": 16,
54
+ "vocab_size": 30000
55
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/albert/hf-internal-testing/tiny-random-AlbertModel/e59dd1535caa6a29b4cc.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-AlbertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "AlbertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout_prob": 0.1,
10
+ "embedding_size": 128,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 36,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 37,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask",
33
+ "token_type_ids"
34
+ ],
35
+ "int_dtype": "int64",
36
+ "model_type": "albert",
37
+ "optlevel": "2",
38
+ "output_attentions": false,
39
+ "output_hidden_states": false,
40
+ "output_names": [
41
+ "logits"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "text-classification",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 6,
49
+ "num_hidden_groups": 6,
50
+ "num_hidden_layers": 6,
51
+ "position_embedding_type": "absolute",
52
+ "type_vocab_size": 16,
53
+ "vocab_size": 30000
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/beit/hf-internal-testing/tiny-random-BeitForImageClassification/7b8399664c54026a03ff.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BeitForImageClassification",
4
+ "_task": "image-classification",
5
+ "add_fpn": false,
6
+ "architectures": [
7
+ "BeitForImageClassification"
8
+ ],
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "auxiliary_channels": 256,
11
+ "auxiliary_concat_input": false,
12
+ "auxiliary_loss_weight": 0.4,
13
+ "auxiliary_num_convs": 1,
14
+ "drop_path_rate": 0.1,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 32,
18
+ "image_size": 30,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 37,
21
+ "layer_norm_eps": 1e-12,
22
+ "layer_scale_init_value": 0.1,
23
+ "model_type": "beit",
24
+ "neuron": {
25
+ "auto_cast": null,
26
+ "auto_cast_type": null,
27
+ "compiler_type": "neuronx-cc",
28
+ "compiler_version": "2.19.8089.0+8ab9f450",
29
+ "disable_fallback": false,
30
+ "disable_fast_relayout": false,
31
+ "dynamic_batch_size": true,
32
+ "float_dtype": "fp32",
33
+ "inline_weights_to_neff": true,
34
+ "input_names": [
35
+ "pixel_values"
36
+ ],
37
+ "int_dtype": "int64",
38
+ "model_type": "beit",
39
+ "optlevel": "2",
40
+ "output_attentions": false,
41
+ "output_hidden_states": false,
42
+ "output_names": [
43
+ "logits"
44
+ ],
45
+ "static_batch_size": 1,
46
+ "static_image_size": 30,
47
+ "static_num_channels": 3,
48
+ "static_patch_size": 2,
49
+ "task": "image-classification",
50
+ "tensor_parallel_size": 1
51
+ },
52
+ "num_attention_heads": 4,
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 4,
55
+ "out_features": [
56
+ "stem",
57
+ "stage1",
58
+ "stage2",
59
+ "stage3"
60
+ ],
61
+ "out_indices": [
62
+ 0,
63
+ 1,
64
+ 2,
65
+ 3
66
+ ],
67
+ "patch_size": 2,
68
+ "pool_scales": [
69
+ 1,
70
+ 2,
71
+ 3,
72
+ 6
73
+ ],
74
+ "reshape_hidden_states": true,
75
+ "semantic_loss_ignore_index": 255,
76
+ "stage_names": [
77
+ "stem",
78
+ "stage1",
79
+ "stage2",
80
+ "stage3",
81
+ "stage4"
82
+ ],
83
+ "use_absolute_position_embeddings": false,
84
+ "use_auxiliary_head": true,
85
+ "use_mask_token": false,
86
+ "use_mean_pooling": true,
87
+ "use_relative_position_bias": false,
88
+ "use_shared_relative_position_bias": false,
89
+ "vocab_size": 100
90
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/beit/hf-internal-testing/tiny-random-BeitForImageClassification/8eea34f80bdd528f4c47.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BeitForImageClassification",
4
+ "_task": "image-classification",
5
+ "add_fpn": false,
6
+ "architectures": [
7
+ "BeitForImageClassification"
8
+ ],
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "auxiliary_channels": 256,
11
+ "auxiliary_concat_input": false,
12
+ "auxiliary_loss_weight": 0.4,
13
+ "auxiliary_num_convs": 1,
14
+ "drop_path_rate": 0.1,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 32,
18
+ "image_size": 30,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 37,
21
+ "layer_norm_eps": 1e-12,
22
+ "layer_scale_init_value": 0.1,
23
+ "model_type": "beit",
24
+ "neuron": {
25
+ "auto_cast": null,
26
+ "auto_cast_type": null,
27
+ "compiler_type": "neuronx-cc",
28
+ "compiler_version": "2.19.8089.0+8ab9f450",
29
+ "disable_fallback": false,
30
+ "disable_fast_relayout": false,
31
+ "dynamic_batch_size": false,
32
+ "float_dtype": "fp32",
33
+ "inline_weights_to_neff": true,
34
+ "input_names": [
35
+ "pixel_values"
36
+ ],
37
+ "int_dtype": "int64",
38
+ "model_type": "beit",
39
+ "optlevel": "2",
40
+ "output_attentions": false,
41
+ "output_hidden_states": false,
42
+ "output_names": [
43
+ "logits"
44
+ ],
45
+ "static_batch_size": 1,
46
+ "static_image_size": 30,
47
+ "static_num_channels": 3,
48
+ "static_patch_size": 2,
49
+ "task": "image-classification",
50
+ "tensor_parallel_size": 1
51
+ },
52
+ "num_attention_heads": 4,
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 4,
55
+ "out_features": [
56
+ "stem",
57
+ "stage1",
58
+ "stage2",
59
+ "stage3"
60
+ ],
61
+ "out_indices": [
62
+ 0,
63
+ 1,
64
+ 2,
65
+ 3
66
+ ],
67
+ "patch_size": 2,
68
+ "pool_scales": [
69
+ 1,
70
+ 2,
71
+ 3,
72
+ 6
73
+ ],
74
+ "reshape_hidden_states": true,
75
+ "semantic_loss_ignore_index": 255,
76
+ "stage_names": [
77
+ "stem",
78
+ "stage1",
79
+ "stage2",
80
+ "stage3",
81
+ "stage4"
82
+ ],
83
+ "use_absolute_position_embeddings": false,
84
+ "use_auxiliary_head": true,
85
+ "use_mask_token": false,
86
+ "use_mean_pooling": true,
87
+ "use_relative_position_bias": false,
88
+ "use_shared_relative_position_bias": false,
89
+ "vocab_size": 100
90
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/Jingya/tiny-random-bert-remote-code/601076bf2990d898404b.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Jingya/tiny-random-bert-remote-code",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "text-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/fxmarty/tiny-bert-sst2-distilled-subfolder/d7d576d06e1491d72e5a.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "fxmarty/tiny-bert-sst2-distilled-subfolder",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertForSequenceClassification"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 128,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "positive"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "negative": "0",
21
+ "positive": "1"
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "neuron": {
27
+ "auto_cast": null,
28
+ "auto_cast_type": null,
29
+ "compiler_type": "neuronx-cc",
30
+ "compiler_version": "2.19.8089.0+8ab9f450",
31
+ "disable_fallback": false,
32
+ "disable_fast_relayout": false,
33
+ "dynamic_batch_size": false,
34
+ "float_dtype": "fp32",
35
+ "inline_weights_to_neff": true,
36
+ "input_names": [
37
+ "input_ids",
38
+ "attention_mask",
39
+ "token_type_ids"
40
+ ],
41
+ "int_dtype": "int64",
42
+ "model_type": "bert",
43
+ "optlevel": "2",
44
+ "output_attentions": false,
45
+ "output_hidden_states": false,
46
+ "output_names": [
47
+ "logits"
48
+ ],
49
+ "static_batch_size": 1,
50
+ "static_sequence_length": 32,
51
+ "task": "text-classification",
52
+ "tensor_parallel_size": 1
53
+ },
54
+ "num_attention_heads": 2,
55
+ "num_hidden_layers": 2,
56
+ "position_embedding_type": "absolute",
57
+ "problem_type": "single_label_classification",
58
+ "type_vocab_size": 2,
59
+ "use_cache": true,
60
+ "vocab_size": 30522
61
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/07d9dac237105afed7b4.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "fill-mask",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/0d7dca7e1b02d11fa30b.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "text-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/22ce2cce0b08d134021c.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "multiple-choice",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_num_choices": 4,
43
+ "static_sequence_length": 128,
44
+ "task": "multiple-choice",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/28bcefedc9caadd676ab.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "last_hidden_state",
40
+ "pooler_output"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 128,
44
+ "task": "feature-extraction",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/3908bf519c210b434176.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "last_hidden_state",
40
+ "pooler_output"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 32,
44
+ "task": "feature-extraction",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/5ead9d705b13f37e716b.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": false,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "text-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/80c925bab2fcc5749b91.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "start_logits",
40
+ "end_logits"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 128,
44
+ "task": "question-answering",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/92f51980d46489605055.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 128,
43
+ "task": "text-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/aeebf3f56cf9d0ed0250.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "token-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/cfb94bae5629e275593f.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "last_hidden_state",
40
+ "pooler_output"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 32,
44
+ "task": "feature-extraction",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e050716b5de372871d73.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 128,
43
+ "task": "token-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e0768f223c51e12fd868.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "fill-mask",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e2594a1f187f452902f7.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 128,
43
+ "task": "fill-mask",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e4834fd951418b796374.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "multiple-choice",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_num_choices": 4,
43
+ "static_sequence_length": 128,
44
+ "task": "multiple-choice",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/e7e71e6beffbf701391b.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": false,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "start_logits",
40
+ "end_logits"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 32,
44
+ "task": "question-answering",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/ea81a963f6aa67da9f09.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "start_logits",
40
+ "end_logits"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 32,
44
+ "task": "question-answering",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1124
53
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/ef32dca934503ba9400c.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "token-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/hf-internal-testing/tiny-random-BertModel/f15944a91bf873bc4059.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-BertModel",
4
+ "_task": "text-classification",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "neuron": {
19
+ "auto_cast": null,
20
+ "auto_cast_type": null,
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.19.8089.0+8ab9f450",
23
+ "disable_fallback": false,
24
+ "disable_fast_relayout": false,
25
+ "dynamic_batch_size": true,
26
+ "float_dtype": "fp32",
27
+ "inline_weights_to_neff": true,
28
+ "input_names": [
29
+ "input_ids",
30
+ "attention_mask",
31
+ "token_type_ids"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "bert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "text-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1124
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/sentence-transformers/all-MiniLM-L6-v2/b571d0d9ac9ad084fa8c.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "sentence-transformers/all-MiniLM-L6-v2",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "export_model_type": "transformer",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 384,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": false,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask"
33
+ ],
34
+ "int_dtype": "int64",
35
+ "model_type": "transformer",
36
+ "optlevel": "2",
37
+ "output_attentions": false,
38
+ "output_hidden_states": false,
39
+ "output_names": [
40
+ "token_embeddings",
41
+ "sentence_embedding"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 16,
45
+ "task": "feature-extraction",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 6,
50
+ "position_embedding_type": "absolute",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 30522
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/bert/sentence-transformers/all-MiniLM-L6-v2/f99a0822ae493faf0bb5.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "sentence-transformers/all-MiniLM-L6-v2",
4
+ "_task": "feature-extraction",
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "export_model_type": "transformer",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 384,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "neuron": {
21
+ "auto_cast": null,
22
+ "auto_cast_type": null,
23
+ "compiler_type": "neuronx-cc",
24
+ "compiler_version": "2.19.8089.0+8ab9f450",
25
+ "disable_fallback": false,
26
+ "disable_fast_relayout": false,
27
+ "dynamic_batch_size": true,
28
+ "float_dtype": "fp32",
29
+ "inline_weights_to_neff": true,
30
+ "input_names": [
31
+ "input_ids",
32
+ "attention_mask"
33
+ ],
34
+ "int_dtype": "int64",
35
+ "model_type": "transformer",
36
+ "optlevel": "2",
37
+ "output_attentions": false,
38
+ "output_hidden_states": false,
39
+ "output_names": [
40
+ "token_embeddings",
41
+ "sentence_embedding"
42
+ ],
43
+ "static_batch_size": 1,
44
+ "static_sequence_length": 32,
45
+ "task": "feature-extraction",
46
+ "tensor_parallel_size": 1
47
+ },
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 6,
50
+ "position_embedding_type": "absolute",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 30522
54
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/16650c04744503a0af47.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-camembert",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "CamembertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "camembert",
19
+ "neuron": {
20
+ "auto_cast": null,
21
+ "auto_cast_type": null,
22
+ "compiler_type": "neuronx-cc",
23
+ "compiler_version": "2.19.8089.0+8ab9f450",
24
+ "disable_fallback": false,
25
+ "disable_fast_relayout": false,
26
+ "dynamic_batch_size": false,
27
+ "float_dtype": "fp32",
28
+ "inline_weights_to_neff": true,
29
+ "input_names": [
30
+ "input_ids",
31
+ "attention_mask"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "camembert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "token-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1000
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/3d5fe21de242b8b602d5.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-camembert",
4
+ "_task": "fill-mask",
5
+ "architectures": [
6
+ "CamembertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "camembert",
19
+ "neuron": {
20
+ "auto_cast": null,
21
+ "auto_cast_type": null,
22
+ "compiler_type": "neuronx-cc",
23
+ "compiler_version": "2.19.8089.0+8ab9f450",
24
+ "disable_fallback": false,
25
+ "disable_fast_relayout": false,
26
+ "dynamic_batch_size": true,
27
+ "float_dtype": "fp32",
28
+ "inline_weights_to_neff": true,
29
+ "input_names": [
30
+ "input_ids",
31
+ "attention_mask"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "camembert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "fill-mask",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1000
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/4b4a4fbbe9d668bcf61e.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-camembert",
4
+ "_task": "token-classification",
5
+ "architectures": [
6
+ "CamembertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "camembert",
19
+ "neuron": {
20
+ "auto_cast": null,
21
+ "auto_cast_type": null,
22
+ "compiler_type": "neuronx-cc",
23
+ "compiler_version": "2.19.8089.0+8ab9f450",
24
+ "disable_fallback": false,
25
+ "disable_fast_relayout": false,
26
+ "dynamic_batch_size": true,
27
+ "float_dtype": "fp32",
28
+ "inline_weights_to_neff": true,
29
+ "input_names": [
30
+ "input_ids",
31
+ "attention_mask"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "camembert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "logits"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_sequence_length": 32,
43
+ "task": "token-classification",
44
+ "tensor_parallel_size": 1
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 5,
48
+ "position_embedding_type": "absolute",
49
+ "type_vocab_size": 16,
50
+ "use_cache": true,
51
+ "vocab_size": 1000
52
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/camembert/hf-internal-testing/tiny-random-camembert/5bca725791b646775427.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "hf-internal-testing/tiny-random-camembert",
4
+ "_task": "question-answering",
5
+ "architectures": [
6
+ "CamembertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "camembert",
19
+ "neuron": {
20
+ "auto_cast": null,
21
+ "auto_cast_type": null,
22
+ "compiler_type": "neuronx-cc",
23
+ "compiler_version": "2.19.8089.0+8ab9f450",
24
+ "disable_fallback": false,
25
+ "disable_fast_relayout": false,
26
+ "dynamic_batch_size": false,
27
+ "float_dtype": "fp32",
28
+ "inline_weights_to_neff": true,
29
+ "input_names": [
30
+ "input_ids",
31
+ "attention_mask"
32
+ ],
33
+ "int_dtype": "int64",
34
+ "model_type": "camembert",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "start_logits",
40
+ "end_logits"
41
+ ],
42
+ "static_batch_size": 1,
43
+ "static_sequence_length": 128,
44
+ "task": "question-answering",
45
+ "tensor_parallel_size": 1
46
+ },
47
+ "num_attention_heads": 4,
48
+ "num_hidden_layers": 5,
49
+ "position_embedding_type": "absolute",
50
+ "type_vocab_size": 16,
51
+ "use_cache": true,
52
+ "vocab_size": 1000
53
+ }