Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

Server: Don't ignore llama.cpp params (#8754)

Browse Source 
* Don't ignore llama.cpp params

* Add fallback for max_tokens
This commit is contained in:
ardfork 2024-08-04 18:16:23 +00:00 committed by GitHub
parent ecf6b7f23e
commit 978ba3d83d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -900,7 +900,7 @@ struct server_context {
slot.params.stream = json_value(data, "stream", false); slot.params.stream = json_value(data, "stream", false);
slot.params.cache_prompt = json_value(data, "cache_prompt", false); slot.params.cache_prompt = json_value(data, "cache_prompt", false);
slot.params.n_predict = json_value(data, "n_predict", default_params.n_predict); slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", default_params.n_predict));
slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k); slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k);
slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p); slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p);
slot.sparams.min_p = json_value(data, "min_p", default_sparams.min_p); slot.sparams.min_p = json_value(data, "min_p", default_sparams.min_p);

18
examples/server/utils.hpp
View File

@ -355,24 +355,6 @@ static json oaicompat_completion_params_parse(
llama_params["__oaicompat"] = true; llama_params["__oaicompat"] = true;
// Map OpenAI parameters to llama.cpp parameters
//
// For parameters that are defined by the OpenAI documentation (e.g.
// temperature), we explicitly specify OpenAI's intended default; we
// need to do that because sometimes OpenAI disagrees with llama.cpp
//
// 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["frequency_penalty"] = json_value(body, "frequency_penalty", 0.0);
llama_params["logit_bias"] = json_value(body, "logit_bias", json::object());
llama_params["n_predict"] = json_value(body, "max_tokens", -1);
llama_params["presence_penalty"] = json_value(body, "presence_penalty", 0.0);
llama_params["seed"] = json_value(body, "seed", LLAMA_DEFAULT_SEED);
llama_params["stream"] = json_value(body, "stream", false);
llama_params["temperature"] = json_value(body, "temperature", 1.0);
llama_params["top_p"] = json_value(body, "top_p", 1.0);
// Apply chat template to the list of messages // Apply chat template to the list of messages
llama_params["prompt"] = format_chat(model, chat_template, body.at("messages")); llama_params["prompt"] = format_chat(model, chat_template, body.at("messages"));