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

server: fix some beginner mistakes

Browse source
This commit is contained in:
Wang Haoran(Robin) 2023-06-22 21:59:12 -07:00
parent cf76195223
commit 7b93b248ef
1 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

14
examples/server/server.cpp
View file

@ -99,15 +99,19 @@ static void server_log(const char * level, const char * function, int line,
// format incomplete utf-8 multibyte character for output // format incomplete utf-8 multibyte character for output
static std::string tokens_to_output_formatted_string(const llama_context * ctx, const llama_token token) { static std::string tokens_to_output_formatted_string(const llama_context * ctx, const llama_token token) {
const std::string out = token == -1 ? "" : llama_token_to_str(ctx, token); std::string out = token == -1 ? "" : llama_token_to_str(ctx, token);
if (out[0] > 127) { // if first bit is 1, meaning it's a partial character
out = "byte: \\x" + std::format("{:x}", out[0]); if ((out[0] & 0x80) == 0x80) {
std::stringstream ss;
ss<< std::hex << (out[0] & 0xff);
std::string res ( ss.str() );
out = "byte: \\x" + res;
} }
return out; return out;
} }
// convert a vector of completion_token_output to json // convert a vector of completion_token_output to json
static json probs_vector_to_json(const llama_context * ctx, const vector<completion_token_output> probs) { static json probs_vector_to_json(const llama_context * ctx, const std::vector<completion_token_output> probs) {
json out = json::array(); json out = json::array();
for (const auto & prob : probs) { for (const auto & prob : probs) {
json probs_for_token = json::array(); json probs_for_token = json::array();
@ -740,7 +744,7 @@ static json format_final_response(llama_server_context & llama, const std::strin
{ "stopped_word", llama.stopped_word }, { "stopped_word", llama.stopped_word },
{ "stopped_limit", llama.stopped_limit }, { "stopped_limit", llama.stopped_limit },
{ "stopping_word", llama.stopping_word }, { "stopping_word", llama.stopping_word },
} };
if (llama.params.n_probs > 0) { if (llama.params.n_probs > 0) {
json completion_probabilities_json = probs_vector_to_json(llama.ctx, probs); json completion_probabilities_json = probs_vector_to_json(llama.ctx, probs);