tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-01 21:04:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : add min_p param (#3877)

Browse Source 
* Update server.cpp with min_p after it was introduced in https://github.com/ggerganov/llama.cpp/pull/3841

* Use spaces instead of tabs

* Update index.html.hpp after running deps.sh

* Fix test - fix line ending
This commit is contained in:
Mihai
2023-11-09 04:00:34 +02:00
committed by GitHub
parent 875fb42871
commit 57ad015dc3
4 changed files with 2211 additions and 2191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/public/index.html
View File

@@ -219,6 +219,7 @@
repeat_penalty: 1.18, // 1.0 = disabled
top_k: 40, // <= 0 to use vocab size
top_p: 0.5, // 1.0 = disabled
min_p: 0.05, // 0 = disabled
tfs_z: 1.0, // 1.0 = disabled
typical_p: 1.0, // 1.0 = disabled
presence_penalty: 0.0, // 0.0 = disabled
@@ -744,6 +745,7 @@
${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
${IntField({ label: "Top-K sampling", max: 100, min: -1, name: "top_k", value: params.value.top_k })}
${FloatField({ label: "Top-P sampling", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p })}
${FloatField({ label: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}
</fieldset>
<details>
<summary>More options</summary>