abetlen / abetlen/llama-cpp-python

Is loading of control vectors supported?

未關閉
#1,363 1 則留言 1 個 reaction 已指派 0 人 在 GitHub 檢視
enhancement
主要語言
Python
星號
10.6k
分支
1.4k
PR 合併指標
PR 指標待擷取

描述

The documentation (https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.llama_cpp.llama_control_vector_apply) mentions

> Apply a loaded control vector to a llama_context, or if data is NULL, clear the currently loaded vector. n_embd should be the size of a single layer's control, and data should point to an n_embd x n_layers buffer starting from layer 1. il_start and il_end are the layer range the vector should apply to (both inclusive) See llama_control_vector_load in common to load a control vector.

I can't find `llama_control_vector_load` in the python api, is there another way to load control vectors?

貢獻指南

開啟貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。