vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Temporarily hard-coded mscale value for DeepSeek-V2 (FIXME!).

Browse source
This commit is contained in:
Stanisław Szymczyk 2024-05-19 12:22:54 +02:00
parent 7e4786bbfb
commit 71a742256c
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml.c
View file

@ -14073,6 +14073,8 @@ static void rope_yarn(
// Get n-d magnitude scaling corrected for interpolation // Get n-d magnitude scaling corrected for interpolation
mscale *= 1.0f + 0.1f * logf(1.0f / freq_scale); mscale *= 1.0f + 0.1f * logf(1.0f / freq_scale);
} }
// TODO ugly hack for DeepSeek-V2 until we find a solution
mscale = 1.0;
*cos_theta = cosf(theta) * mscale; *cos_theta = cosf(theta) * mscale;
*sin_theta = sinf(theta) * mscale; *sin_theta = sinf(theta) * mscale;
} }