llama_model_quantize_params class final

Inheritance

Implemented types

Available extensions

Constructors

address → Pointer<T>: Available on T, provided by the StructAddress extension
The memory address of the underlying data.
no setter
allow_requantize ↔ bool: getter/setter pair
ftype → llama_ftype: no setter
ftypeAsInt ↔ int: getter/setter pair
hashCode → int: The hash code for this object.
no setterinherited
imatrix ↔ Pointer<Void>: getter/setter pair
keep_split ↔ bool: getter/setter pair
kv_overrides ↔ Pointer<Void>: getter/setter pair
nthread ↔ int: getter/setter pair
only_copy ↔ bool: getter/setter pair
output_tensor_type → ggml_type: no setter
output_tensor_typeAsInt ↔ int: getter/setter pair
prune_layers ↔ Pointer<Void>: getter/setter pair
pure ↔ bool: getter/setter pair
quantize_output_tensor ↔ bool: getter/setter pair
runtimeType → Type: A representation of the runtime type of the object.
no setterinherited
tensor_types ↔ Pointer<Void>: getter/setter pair
token_embedding_type → ggml_type: no setter
token_embedding_typeAsInt ↔ int: getter/setter pair

noSuchMethod(Invocation invocation) → dynamic: Invoked when a nonexistent method or property is accessed.
inherited
toString() → String: A string representation of this object.
inherited