Skip to content
Closed
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
6 changes: 3 additions & 3 deletions examples/batched.swift/Sources/main.swift
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,7 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
let utf8Count = text.utf8.count
let n_tokens = utf8Count + (add_bos ? 1 : 0)
let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
let tokenCount = llama_tokenize(llama_model_get_vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
var swiftTokens: [llama_token] = []
for i in 0 ..< tokenCount {
swiftTokens.append(tokens[Int(i)])
Expand All @@ -218,12 +218,12 @@ 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), 0, false)
let nTokens = llama_token_to_piece(llama_model_get_vocab, token, &result, Int32(result.count), 0, false)
if nTokens < 0 {
let actualTokensCount = -Int(nTokens)
result = .init(repeating: 0, count: actualTokensCount)
let check = llama_token_to_piece(
model,
llama_model_get_vocab,
token,
&result,
Int32(result.count),
Expand Down
8 changes: 4 additions & 4 deletions examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ actor LlamaContext {

new_token_id = llama_sampler_sample(sampling, context, batch.n_tokens - 1)

if llama_vocab_is_eog(model, new_token_id) || n_cur == n_len {
if llama_vocab_is_eog(llama_model_get_vocab, new_token_id) || n_cur == n_len {
print("\n")
is_done = true
let new_token_str = String(cString: temporary_invalid_cchars + [0])
Expand Down Expand Up @@ -297,7 +297,7 @@ actor LlamaContext {
let utf8Count = text.utf8.count
let n_tokens = utf8Count + (add_bos ? 1 : 0) + 1
let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)
let tokenCount = llama_tokenize(llama_model_get_vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)

var swiftTokens: [llama_token] = []
for i in 0..<tokenCount {
Expand All @@ -316,15 +316,15 @@ actor LlamaContext {
defer {
result.deallocate()
}
let nTokens = llama_token_to_piece(model, token, result, 8, 0, false)
let nTokens = llama_token_to_piece(llama_model_get_vocab, token, result, 8, 0, false)

if nTokens < 0 {
let newResult = UnsafeMutablePointer<Int8>.allocate(capacity: Int(-nTokens))
newResult.initialize(repeating: Int8(0), count: Int(-nTokens))
defer {
newResult.deallocate()
}
let nNewTokens = llama_token_to_piece(model, token, newResult, -nTokens, 0, false)
let nNewTokens = llama_token_to_piece(llama_model_get_vocab, token, newResult, -nTokens, 0, false)
let bufferPointer = UnsafeBufferPointer(start: newResult, count: Int(nNewTokens))
return Array(bufferPointer)
} else {
Expand Down
Loading