vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-05 23:41:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)

Browse source 
* models : fix the attn_factor for mistral3 graphs

* cont : rework attn_factor correction logic

* cont : make deepseek2 consistent

* cont : add TODO

* cont : special-case DSv2

* cont : revert Mistral 3 Large changes

* cont : fix DS2 to use the original attn_factor

* cont : minor comments
This commit is contained in:
Georgi Gerganov 2025-12-12 17:12:40 +02:00 • committed by GitHub
parent dcb7d17758
commit 7bed317f53
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 78 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-graph.cpp
View file

@ -574,7 +574,7 @@ llm_graph_context::llm_graph_context(const llm_graph_params & params) :
freq_base (cparams.rope_freq_base),
freq_scale (cparams.rope_freq_scale),
ext_factor (cparams.yarn_ext_factor),
attn_factor (cparams.yarn_attn_factor),
attn_factor (llama_hparams::yarn_attn_factor_adjust(cparams.yarn_attn_factor, cparams.rope_freq_scale, cparams.yarn_ext_factor)),
beta_fast (cparams.yarn_beta_fast),
beta_slow (cparams.yarn_beta_slow),
norm_eps (hparams.f_norm_eps),