tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : remove Tail-Free sampling (#10071)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-10-29 10:42:05 +02:00
committed by GitHub
parent 61715d5cc8
commit 8d8ff71536
16 changed files with 15 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/utils.hpp
View File

@ -607,7 +607,7 @@ static json oaicompat_completion_params_parse(
}
// Copy remaining properties to llama_params
// This allows user to use llama.cpp-specific params like "mirostat", "tfs_z",... via OAI endpoint.
// This allows user to use llama.cpp-specific params like "mirostat", ... via OAI endpoint.
// See "launch_slot_with_task()" for a complete list of params supported by llama.cpp
for (const auto & item : body.items()) {
// Exception: if "n_predict" is present, we overwrite the value specified earlier by "max_tokens"