From 40f74e4d739e9250431cf339ae7588b28d8d0663 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 21 Apr 2024 18:36:45 +0300 Subject: llama : add option to render special/control tokens (#6807) * make : fix common dep on llama.h * llama : add option to render special tokens * readme : add API change notice ggml-ci * swift : fix build --- examples/llama.swiftui/llama.cpp.swift/LibLlama.swift | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'examples/llama.swiftui/llama.cpp.swift') diff --git a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift index 70c43a38..737f882f 100644 --- a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift +++ b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift @@ -322,7 +322,7 @@ actor LlamaContext { defer { result.deallocate() } - let nTokens = llama_token_to_piece(model, token, result, 8) + let nTokens = llama_token_to_piece(model, token, result, 8, false) if nTokens < 0 { let newResult = UnsafeMutablePointer.allocate(capacity: Int(-nTokens)) @@ -330,7 +330,7 @@ actor LlamaContext { defer { newResult.deallocate() } - let nNewTokens = llama_token_to_piece(model, token, newResult, -nTokens) + let nNewTokens = llama_token_to_piece(model, token, newResult, -nTokens, false) let bufferPointer = UnsafeBufferPointer(start: newResult, count: Int(nNewTokens)) return Array(bufferPointer) } else { -- cgit v1.2.3