Llama
- AdapterLora
  - AttachmentLease
  - Error
- Batch
  - Error
- BusyError
- Cancellation
- Chat
- ChatMessage
- ClosedError
- Context
  - Error
- ContextFullError
- ContextOptions
- DecodeError
  - Reason
- Embedder
- EmbeddingError
- Error
- FinishReason
- Generation
- GenerationChunk
- GenerationOptions
- Generator
- IncompatibleLibraryError
- LazyMode
- Memory
  - Error
- Message
- Model
  - ChildCreationLease
  - Error
- ModelOptions
- NativeResource
- Pooling
- RuntimeInfo
- Sampler
  - AdaptiveP
  - Base
  - Dist
  - Error
  - Grammar
  - GrammarLazyPatterns
  - Greedy
  - Infill
  - MinP
  - Mirostat
  - MirostatV2
  - Penalties
  - Temp
  - TempExt
  - TopK
  - TopNSigma
  - TopP
  - Typical
  - Xtc
- SamplerChain
- Sampling
  - Distribution
  - Grammar
  - Greedy
  - MinP
  - Plan
  - Stage
  - Temperature
  - TopK
- Session
- SessionSnapshot
- State
  - Error
- StateCompatibilityError
- StopDetector
- StreamingDecoder
- TemplateError
- Token
- TokenizationError
- UnsupportedOperationError
- Usage
- Vocab

alias Llama::Token

Alias Definition

Int32

Defined in:

llama/result.cr