vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Revert code motion

Browse source
This commit is contained in:
goerch 2023-10-22 18:36:35 +02:00
parent 6a94ae6d49
commit 8ee736370a
1 changed files with 15 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

30
llama.cpp
View file

@ -975,6 +975,21 @@ static void llama_nop(struct ggml_tensor * tensor) { // don't offload by default
(void) tensor; (void) tensor;
} }
static std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token) {
std::vector<char> result(8, 0);
const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size());
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size());
GGML_ASSERT(check == -n_tokens);
}
else {
result.resize(n_tokens);
}
return std::string(result.data(), result.size());
}
// //
// globals // globals
// //
@ -7447,21 +7462,6 @@ void llama_sample_repetition_penalties(
} }
} }
static std::string llama_token_to_piece(const struct llama_context* ctx, llama_token token) {
std::vector<char> result(8, 0);
const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size());
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size());
GGML_ASSERT(check == -n_tokens);
}
else {
result.resize(n_tokens);
}
return std::string(result.data(), result.size());
}
void llama_sample_grammar(struct llama_context * ctx, llama_token_data_array * candidates, const struct llama_grammar * grammar) { void llama_sample_grammar(struct llama_context * ctx, llama_token_data_array * candidates, const struct llama_grammar * grammar) {
GGML_ASSERT(ctx); GGML_ASSERT(ctx);
const int64_t t_start_sample_us = ggml_time_us(); const int64_t t_start_sample_us = ggml_time_us();