Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,7 @@ enum ComputeUnits: String, ExpressibleByArgument, CaseIterable {

/// Returns a cleaned and formatted version of the response.
///
/// - Parameter respone: The response to clean and format.
/// - Parameter response: The response to clean and format.
/// - Returns: A 'user friendly' representation of the generated response.
private func formatResponse(_ response: String) -> String {
response
Expand Down
3 changes: 1 addition & 2 deletions Sources/Models/LanguageModel.swift
Original file line number Diff line number Diff line change
Expand Up @@ -236,8 +236,7 @@ public extension LanguageModel {

/// Determines the type of KV Cache available for the model, if any.
///
/// - Parameters:
/// - model: The Core ML model
/// - Parameter model: The Core ML model
/// - Returns: The type of KV Cache available.
fileprivate static func kvCacheAvailability(for model: MLModel) -> KVCacheAvailability? {
func isStatefulKVCacheAvailable(for model: MLModel) -> Bool {
Expand Down
6 changes: 3 additions & 3 deletions Sources/Models/LanguageModelTypes.swift
Original file line number Diff line number Diff line change
Expand Up @@ -57,9 +57,9 @@ public extension LanguageModelProtocol {
/// This provides a more convenient syntax for calling `predictNextTokenScores`.
///
/// - Parameters:
/// - tokens: The input token sequence
/// - config: The generation configuration containing model parameters
/// - Returns: A shaped array containing the logits for the next token prediction
/// - input: The input sequence tensor.
/// - config: The generation configuration containing model parameters.
/// - Returns: MLTensor with the raw scores of the next token.
func callAsFunction(_ input: MLTensor, config: GenerationConfig) async -> MLTensor {
await predictNextTokenScores(input, config: config)
}
Expand Down
Loading