tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 14:15:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Server: use llama_chat_apply_template (#5593)

Browse Source 
* server: use llama_chat_apply_template

* server: remove trailing space

* server: fix format_chat

* server: fix help message

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server: fix formatted_chat

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan Son Nguyen
2024-02-20 15:58:27 +01:00
committed by GitHub
parent 5207b3fbc5
commit 9c405c9f9a
4 changed files with 45 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/server/oai.hpp
View File

@ -15,13 +15,11 @@
using json = nlohmann::json;
inline static json oaicompat_completion_params_parse(
const struct llama_model * model,
const json &body, /* openai api json semantics */
const std::string &chat_template)
{
json llama_params;
std::string formatted_prompt = chat_template == "chatml"
? format_chatml(body["messages"]) // OpenAI 'messages' to chatml (with <|im_start|>,...)
: format_llama2(body["messages"]); // OpenAI 'messages' to llama2 (with [INST],...)
llama_params["__oaicompat"] = true;
@ -34,7 +32,7 @@ inline static json oaicompat_completion_params_parse(
// https://platform.openai.com/docs/api-reference/chat/create
llama_sampling_params default_sparams;
llama_params["model"] = json_value(body, "model", std::string("unknown"));
llama_params["prompt"] = formatted_prompt;
llama_params["prompt"] = format_chat(model, chat_template, body["messages"]);
llama_params["cache_prompt"] = json_value(body, "cache_prompt", false);
llama_params["temperature"] = json_value(body, "temperature", 0.0);
llama_params["top_k"] = json_value(body, "top_k", default_sparams.top_k);