nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity
9,160 Commits 1 Branch 0 Tags
7155a49771279063a8b9b647d33347811abc64c3
Commit Graph
6 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
AndreiGitHubslaren
 		1c5eba6f8e llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197) 
* Add attention and final logit softcapping.

* fix

* Add custom add_ functions

* Disable flash attention for Gemma2

* Update src/llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* Add default value for attention and final logit softcap value

* Add custom kq scaling from Gemma2Attention

* Remove custom pre attention scaling and use computed value instead.

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-06-29 23:44:08 -04:00
AndreiandGitHub d11afd6652 llava : fix moondream support (#7163) 
* Revert "Revert "llava : add support for moondream vision language model (#6899)""

This reverts commit 9da243b36a.

* Fix num_positions and embeddings initialization
 2024-05-10 09:41:10 +03:00
AndreiandGitHub 51b2fc11f7 cmake : fix relative path to git submodule index (#3915) 2023-11-02 21:40:31 +02:00
AndreiandGitHub 76164fe2e6 cmake : fix llama.h location when built outside of root directory (#3179) 2023-09-15 11:07:40 +03:00
AndreiandGitHub 769266a543 cmake : compile ggml-rocm with -fpic when building shared library (#3158) 2023-09-14 20:38:16 +03:00
AndreiandGitHub 303f5809f1 metal : fix issue with ggml-metal.metal path. Closes #1769 (#1782) 
* Fix issue with ggml-metal.metal path

* Add ggml-metal.metal as a resource for llama target

* Update flake.nix metal kernel substitution
 2023-06-10 17:47:34 +03:00