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

doc: minor

Browse source 
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
This commit is contained in:
Pierrick Hymbert 2024-12-28 19:38:08 +01:00 • committed by Georgi Gerganov
parent e0e23b5c37
commit 3199b2f301
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/development/HOWTO-add-model.md
View file

@ -96,7 +96,7 @@ NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorc
This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `llama_build_graph`. This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `llama_build_graph`.
Have a look at existing implementation like `build_llama`, `build_dbrx` or `build_bert`. Have a look at existing implementations like `build_llama`, `build_dbrx` or `build_bert`.
Some `ggml` backends do not support all operations. Backend implementations can be added in a separate PR. Some `ggml` backends do not support all operations. Backend implementations can be added in a separate PR.