dacorvo HF staff commited on
Commit
2af9f87
1 Parent(s): a92cfe3

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 +124 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/meta-llama/CodeLlama-7b-Instruct-hf/e4d3f9d8d335e8c2ff1f.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/2c73925e46a18751b152.json +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/7b3393a7c5fd984a34d9.json +1 -0
  5. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/c997564eba3d6777671f.json +1 -0
  6. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/02b3df5661ef8ff79cc0.json +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/4151c6889dcf1584205c.json +1 -0
  8. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/6d5c143cd18bfcd9f4af.json +1 -0
  9. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/720f4c07d5f83b2ff9d4.json +1 -0
  10. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/874f10ed32bff7260c79.json +1 -0
  11. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/befa24d60d5bca012c3b.json +1 -0
  12. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1fb2d1d6f793fd1c9744.json +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/65314683f5d624301ac7.json +1 -0
  14. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/bba017603eba49cc3a1f.json +1 -0
  15. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/f32b4f1b111de9eb757b.json +1 -0
  16. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/180283e8bf01ae3507c0.json +1 -0
  17. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/39a7649c623c1888c776.json +1 -0
  18. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/54e96fc83b91f9ca40c8.json +1 -0
  19. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/157730f634afe14ca3bc.json +1 -0
  20. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/1caf4d7e91344cb4edd4.json +1 -0
  21. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/a5d3d8806cd364c7a404.json +1 -0
  22. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/cc9c0a9006808dddfa27.json +1 -0
  23. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/54d2c115427eb106b498.json +1 -0
  24. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/55063f94fc7dddda3ac1.json +1 -0
  25. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/832467c16a81d475fbb1.json +1 -0
  26. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/9a95ca98317aed241916.json +1 -0
  27. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/a246f0054be6283dfb7e.json +1 -0
  28. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/b92e78445e785f8ec26d.json +1 -0
  29. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/f1b87f52657555ab6e8e.json +1 -0
  30. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json +1 -0
  31. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/1b591b403ed491d5ab63.json +1 -0
  32. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/64100d76dcead9899788.json +1 -0
  33. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/71db595b7dfd053ae87e.json +1 -0
  34. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/722c51fa693dfe7976b7.json +1 -0
  35. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/optimum/mistral-1.1b-testing/0d3dcdfa46156c785a82.json +1 -0
  36. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/000f1688e11ccb68df60.json +1 -0
  37. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/089a1107126e0bb3ee3d.json +1 -0
  38. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/1d304ff5d8161c76d511.json +1 -0
  39. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/abfe2aa64af6a13ba7f8.json +1 -0
  40. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/09dbce9d84c145ef699b.json +1 -0
  41. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/10b079960341f41cb11b.json +1 -0
  42. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/ddbc5f019bf5542a2be6.json +1 -0
  43. neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/compile_flags.txt +1 -0
  44. neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.hlo_module.pb +3 -0
  45. neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff +3 -0
  46. neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/compile_flags.txt +1 -0
  47. neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.hlo_module.pb +3 -0
  48. neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff +3 -0
  49. neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/compile_flags.txt +1 -0
  50. neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.hlo_module.pb +3 -0
.gitattributes CHANGED
@@ -5073,3 +5073,127 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_25f8e9385616f2386b3a/model.neuron filter=lf
5073
  neuronxcc-2.15.128.0+56dc5a86/MODULE_312febc892ba028f4783/model.neuron filter=lfs diff=lfs merge=lfs -text
5074
  neuronxcc-2.15.128.0+56dc5a86/MODULE_96f2e7f66c8c4a2049c5/model.neuron filter=lfs diff=lfs merge=lfs -text
5075
  neuronxcc-2.15.128.0+56dc5a86/MODULE_f4dd705de07c8a349cae/model.neuron filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5073
  neuronxcc-2.15.128.0+56dc5a86/MODULE_312febc892ba028f4783/model.neuron filter=lfs diff=lfs merge=lfs -text
5074
  neuronxcc-2.15.128.0+56dc5a86/MODULE_96f2e7f66c8c4a2049c5/model.neuron filter=lfs diff=lfs merge=lfs -text
5075
  neuronxcc-2.15.128.0+56dc5a86/MODULE_f4dd705de07c8a349cae/model.neuron filter=lfs diff=lfs merge=lfs -text
5076
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5077
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5078
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5079
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5080
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5081
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5082
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5083
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5084
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5085
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5086
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5087
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5088
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5089
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5090
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5091
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5092
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5093
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5094
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5095
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5096
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5097
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5098
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5099
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5100
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5101
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5102
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5103
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5104
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5105
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5106
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5107
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5108
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5109
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5110
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
5111
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5112
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5113
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5114
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_06636daaadf79562db13+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5115
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_0a848f64ab3ba788a8a7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5116
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5117
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5118
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5119
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5120
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5121
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5122
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1430632f31ac9e097786+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5123
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5124
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5125
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5126
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5127
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5128
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5129
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_2a756705ae41451bdd91+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5130
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_2d0ecf614fab08ba3e3a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5131
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5132
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5133
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5134
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_3d2012ded37f7e045fe7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5135
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5136
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_4164a8ba56c1777c9b02+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5137
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5138
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5139
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5140
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5141
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_58d0bf37135d5f86b981+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5142
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5143
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5144
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5145
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5146
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5147
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_633ab94b2d987f84967d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5148
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_63e06f8c133abeece2ff+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5149
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_677971d7856e73f86fd8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5150
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5151
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5152
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5153
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5154
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5155
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5156
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_7c0801da95a6c1ed7e30+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5157
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5158
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5159
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5160
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5161
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5162
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5163
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5164
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5165
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5166
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a07a000f4aa986d9fd28+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5167
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5168
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a140efb3351c8d199e2c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5169
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5170
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5171
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_a99da8b7c6d00f75a130+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5172
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5173
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5174
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5175
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5176
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_bbf8f266dde11f6232c8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5177
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_bc1e7bba65773bae73fb+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5178
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5179
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5180
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5181
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5182
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5183
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5184
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5185
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5186
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5187
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5188
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_e049342bf50290d2724f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5189
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_e74e42052287a9d269b6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5190
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_e75ae599b9ad78a80b9b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5191
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5192
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5193
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ede85a6c2ef194dd17ba+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5194
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5195
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_efe3043beb76da374beb+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5196
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5197
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5198
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5199
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/meta-llama/CodeLlama-7b-Instruct-hf/e4d3f9d8d335e8c2ff1f.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/CodeLlama-7b-Instruct-hf", "checkpoint_revision": "4ce0c40b2ea823bd1d8f1f3fd5bc8a7e80d749bc", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32016}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/2c73925e46a18751b152.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/7b3393a7c5fd984a34d9.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/c997564eba3d6777671f.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/02b3df5661ef8ff79cc0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 64, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/4151c6889dcf1584205c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 32, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/6d5c143cd18bfcd9f4af.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 128, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/720f4c07d5f83b2ff9d4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/874f10ed32bff7260c79.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 64, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 128, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/befa24d60d5bca012c3b.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1fb2d1d6f793fd1c9744.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/65314683f5d624301ac7.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/bba017603eba49cc3a1f.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 512, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/f32b4f1b111de9eb757b.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/180283e8bf01ae3507c0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/39a7649c623c1888c776.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/54e96fc83b91f9ca40c8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/157730f634afe14ca3bc.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "d62e0c7237c7b851e8d9ae9277f9f107d174542c", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/1caf4d7e91344cb4edd4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 256, "max_position_embeddings": 512, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-llama", "checkpoint_revision": "7fdafd2fe6a2d31c6abb72ae60db606d8bb23196", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 1, "num_hidden_layers": 1, "num_key_value_heads": 1, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/a5d3d8806cd364c7a404.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 256, "max_position_embeddings": 512, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-llama", "checkpoint_revision": "7fdafd2fe6a2d31c6abb72ae60db606d8bb23196", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 1, "num_hidden_layers": 1, "num_key_value_heads": 1, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/dacorvo/tiny-random-llama/cc9c0a9006808dddfa27.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 256, "max_position_embeddings": 512, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-llama", "checkpoint_revision": "7fdafd2fe6a2d31c6abb72ae60db606d8bb23196", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 1, "num_hidden_layers": 1, "num_key_value_heads": 1, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/54d2c115427eb106b498.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 8192, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/55063f94fc7dddda3ac1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/832467c16a81d475fbb1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/9a95ca98317aed241916.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 8192, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/a246f0054be6283dfb7e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/b92e78445e785f8ec26d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/f1b87f52657555ab6e8e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/1b591b403ed491d5ab63.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "checkpoint_revision": "5206a32e0bd3067aef1ce90f5528ade7d866253f", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/64100d76dcead9899788.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/71db595b7dfd053ae87e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/722c51fa693dfe7976b7.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mistral/optimum/mistral-1.1b-testing/0d3dcdfa46156c785a82.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "optimum/mistral-1.1b-testing", "checkpoint_revision": "ce03bc8d47dbd2c173ff65f3a8de1325ba724195", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/000f1688e11ccb68df60.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/089a1107126e0bb3ee3d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/1d304ff5d8161c76d511.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/mixtral/dacorvo/Mixtral-tiny/abfe2aa64af6a13ba7f8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/09dbce9d84c145ef699b.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/10b079960341f41cb11b.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/ddbc5f019bf5542a2be6.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8e8daf6532c7ead9f96cb22a851fa5f5465806aa4650fed38b0670e63a2872
3
+ size 405658
neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f987b57583f4739daa220d72544bc18b9c78e20ac7e62b76232d9daad774284
3
+ size 19508224
neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed1245ea53f899f203393f819f171f96c1e84311a192afe32ce923432b378aa
3
+ size 263859
neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8749dd44b2b1c4f9ac28dd73f12f7cdd62d274e45f7031ac573be143f5b159b7
3
+ size 1711104
neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76060ba0acde6101e4b19635759494e2738bcb9f409dac02f9450d1f97c9111b
3
+ size 9926