LlamaController constructor

LlamaController({
  1. required String modelPath,
  2. bool? vocabOnly,
  3. bool? useMmap,
  4. bool? useMlock,
  5. bool? checkTensors,
  6. int? nCtx,
  7. int? nBatch,
  8. int? nUBatch,
  9. int? nSeqMax,
  10. int? nThreads,
  11. int? nThreadsBatch,
  12. RopeScalingType? ropeScalingType,
  13. PoolingType? poolingType,
  14. AttentionType? attentionType,
  15. double? ropeFrequencyBase,
  16. double? ropeFrequencyScale,
  17. double? yarnExtrapolationFactor,
  18. double? yarnAttenuationFactor,
  19. double? yarnBetaFast,
  20. double? yarnBetaSlow,
  21. int? yarnOriginalContext,
  22. double? defragmentationThreshold,
  23. GgmlType? typeK,
  24. GgmlType? typeV,
  25. bool? embeddings,
  26. bool? offloadKqv,
  27. bool? flashAttention,
  28. bool? noPerformance,
  29. bool? greedy,
  30. bool? infill,
  31. int? seed,
  32. int? topK,
  33. double? topP,
  34. int? minKeepTopP,
  35. double? minP,
  36. int? minKeepMinP,
  37. double? typicalP,
  38. int? minKeepTypicalP,
  39. double? temperature,
  40. double? temperatureDelta,
  41. double? temperatureExponent,
  42. double? xtcP,
  43. double? xtcT,
  44. int? minKeepXtc,
  45. int? xtcSeed,
  46. int? mirostatNVocab,
  47. int? mirostatSeed,
  48. double? mirostatTau,
  49. double? mirostatEta,
  50. int? mirostatM,
  51. int? mirostatV2Seed,
  52. double? mirostatV2Tau,
  53. double? mirostatV2Eta,
  54. String? grammarStr,
  55. String? grammarRoot,
  56. int? penaltiesLastN,
  57. double? penaltiesRepeat,
  58. double? penaltiesFrequency,
  59. double? penaltiesPresent,
  60. int? drySamplerNCtxTrain,
  61. double? drySamplerMultiplier,
  62. double? drySamplerDryBase,
  63. int? drySamplerAllowedLength,
})

Creates a new instance of LlamaController.

Implementation

LlamaController({
  required String modelPath,
  bool? vocabOnly,
  bool? useMmap,
  bool? useMlock,
  bool? checkTensors,
  int? nCtx,
  int? nBatch,
  int? nUBatch,
  int? nSeqMax,
  int? nThreads,
  int? nThreadsBatch,
  RopeScalingType? ropeScalingType,
  PoolingType? poolingType,
  AttentionType? attentionType,
  double? ropeFrequencyBase,
  double? ropeFrequencyScale,
  double? yarnExtrapolationFactor,
  double? yarnAttenuationFactor,
  double? yarnBetaFast,
  double? yarnBetaSlow,
  int? yarnOriginalContext,
  double? defragmentationThreshold,
  GgmlType? typeK,
  GgmlType? typeV,
  bool? embeddings,
  bool? offloadKqv,
  bool? flashAttention,
  bool? noPerformance,
  bool? greedy,
  bool? infill,
  int? seed,
  int? topK,
  double? topP,
  int? minKeepTopP,
  double? minP,
  int? minKeepMinP,
  double? typicalP,
  int? minKeepTypicalP,
  double? temperature,
  double? temperatureDelta,
  double? temperatureExponent,
  double? xtcP,
  double? xtcT,
  int? minKeepXtc,
  int? xtcSeed,
  int? mirostatNVocab,
  int? mirostatSeed,
  double? mirostatTau,
  double? mirostatEta,
  int? mirostatM,
  int? mirostatV2Seed,
  double? mirostatV2Tau,
  double? mirostatV2Eta,
  String? grammarStr,
  String? grammarRoot,
  int? penaltiesLastN,
  double? penaltiesRepeat,
  double? penaltiesFrequency,
  double? penaltiesPresent,
  int? drySamplerNCtxTrain,
  double? drySamplerMultiplier,
  double? drySamplerDryBase,
  int? drySamplerAllowedLength,
}) : _modelPath = modelPath,
     _vocabOnly = vocabOnly,
     _useMmap = useMmap,
     _useMlock = useMlock,
     _checkTensors = checkTensors,
     _nCtx = nCtx ?? 0,
     _nBatch = nBatch,
     _nUBatch = nUBatch,
     _nSeqMax = nSeqMax,
     _nThreads = nThreads,
     _nThreadsBatch = nThreadsBatch,
     _ropeScalingType = ropeScalingType,
     _poolingType = poolingType,
     _attentionType = attentionType,
     _ropeFrequencyBase = ropeFrequencyBase,
     _ropeFrequencyScale = ropeFrequencyScale,
     _yarnExtrapolationFactor = yarnExtrapolationFactor,
     _yarnAttenuationFactor = yarnAttenuationFactor,
     _yarnBetaFast = yarnBetaFast,
     _yarnBetaSlow = yarnBetaSlow,
     _yarnOriginalContext = yarnOriginalContext,
     _defragmentationThreshold = defragmentationThreshold,
     _typeK = typeK,
     _typeV = typeV,
     _embeddings = embeddings,
     _offloadKqv = offloadKqv,
     _flashAttention = flashAttention,
     _noPerformance = noPerformance,
     _greedy = greedy ?? false,
     _infill = infill ?? false,
     _seed = seed,
     _topK = topK,
     _topP = topP,
     _minKeepTopP = minKeepTopP,
     _minP = minP,
     _minKeepMinP = minKeepMinP,
     _typicalP = typicalP,
     _minKeepTypicalP = minKeepTypicalP,
     _temperature = temperature,
     _temperatureDelta = temperatureDelta,
     _temperatureExponent = temperatureExponent,
     _xtcP = xtcP,
     _xtcT = xtcT,
     _minKeepXtc = minKeepXtc,
     _xtcSeed = xtcSeed,
     _mirostatNVocab = mirostatNVocab,
     _mirostatSeed = mirostatSeed,
     _mirostatTau = mirostatTau,
     _mirostatEta = mirostatEta,
     _mirostatM = mirostatM,
     _mirostatV2Seed = mirostatV2Seed,
     _mirostatV2Tau = mirostatV2Tau,
     _mirostatV2Eta = mirostatV2Eta,
     _grammarStr = grammarStr,
     _grammarRoot = grammarRoot,
     _penaltiesLastN = penaltiesLastN,
     _penaltiesRepeat = penaltiesRepeat,
     _penaltiesFrequency = penaltiesFrequency,
     _penaltiesPresent = penaltiesPresent,
     _drySamplerNCtxTrain = drySamplerNCtxTrain,
     _drySamplerMultiplier = drySamplerMultiplier,
     _drySamplerDryBase = drySamplerDryBase,
     _drySamplerAllowedLength = drySamplerAllowedLength;