highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 13:17:33 +01:00
Code Issues Packages Projects Releases Wiki Activity

revert tokenize ffi (#4761)

Browse Source 
* Revert "use `int32_t` for call to tokenize (#4738)"

This reverts commit 763bb65dbb.

* Revert "vocab only"

This reverts commit bf54c845e9.

* Revert "use ffi for tokenizing/detokenizing"

This reverts commit 26a00a0410.
This commit is contained in:
Michael Yang
2024-05-31 18:54:21 -07:00
committed by GitHub
parent f6b622c4b3
commit 829ff87bd1
3 changed files with 144 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
llm/ext_server/server.cpp vendored
View File

@@ -2625,6 +2625,21 @@ static json format_partial_response(
return res;
}
static json format_tokenizer_response(const std::vector<llama_token> &tokens)
{
return json {
{"tokens", tokens}
};
}
static json format_detokenized_response(std::string content)
{
return json {
{"content", content}
};
}
static void log_server_request(const httplib::Request &req, const httplib::Response &res)
{
// skip GH copilot requests when using default port
@@ -3114,6 +3129,34 @@ int main(int argc, char **argv) {
}
});
svr.Post("/tokenize", [&llama](const httplib::Request &req, httplib::Response &res)
{
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
const json body = json::parse(req.body);
std::vector<llama_token> tokens;
if (body.count("content") != 0)
{
tokens = llama.tokenize(body["content"], false);
}
const json data = format_tokenizer_response(tokens);
return res.set_content(data.dump(), "application/json; charset=utf-8");
});
svr.Post("/detokenize", [&llama](const httplib::Request &req, httplib::Response &res)
{
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
const json body = json::parse(req.body);
std::string content;
if (body.count("tokens") != 0)
{
const std::vector<llama_token> tokens = body["tokens"];
content = tokens_to_str(llama.ctx, tokens.cbegin(), tokens.cend());
}
const json data = format_detokenized_response(content);
return res.set_content(data.dump(), "application/json; charset=utf-8");
});
svr.Post("/embedding", [&llama](const httplib::Request &req, httplib::Response &res)
{
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));