mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-27 12:05:03 +00:00
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
This commit is contained in:
@ -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 {
|
||||
|
Reference in New Issue
Block a user