diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-04-21 18:36:45 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-21 18:36:45 +0300 |
| commit | 40f74e4d739e9250431cf339ae7588b28d8d0663 (patch) | |
| tree | 6008461e7a055c9b86c39df7117b943f1ecc0598 /examples | |
| parent | b9cc76d87e3d7ae5900f19d4fe8f8976d0a35888 (diff) | |
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
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/batched.swift/Sources/main.swift | 5 | ||||
| -rw-r--r-- | examples/llama.swiftui/llama.cpp.swift/LibLlama.swift | 4 |
2 files changed, 5 insertions, 4 deletions
diff --git a/examples/batched.swift/Sources/main.swift b/examples/batched.swift/Sources/main.swift index 5764acb6..dbbd06da 100644 --- a/examples/batched.swift/Sources/main.swift +++ b/examples/batched.swift/Sources/main.swift @@ -229,7 +229,7 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] { private func token_to_piece(token: llama_token, buffer: inout [CChar]) -> String? { var result = [CChar](repeating: 0, count: 8) - let nTokens = llama_token_to_piece(model, token, &result, Int32(result.count)) + let nTokens = llama_token_to_piece(model, token, &result, Int32(result.count), false) if nTokens < 0 { let actualTokensCount = -Int(nTokens) result = .init(repeating: 0, count: actualTokensCount) @@ -237,7 +237,8 @@ private func token_to_piece(token: llama_token, buffer: inout [CChar]) -> String model, token, &result, - Int32(result.count) + Int32(result.count), + false ) assert(check == actualTokensCount) } else { 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<Int8>.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 { |