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

Implement the OLMo architecture (#6741)

Browse source 
* implement olmo architecture

* remove unused variable

* remove unused moe branch

* remove check for weight

* remove superfluous moe, bias and rope tensors

* clarified comment

* fix clamp_kqv setting

* remove obsolete parameter name filter
This commit is contained in:
nopperl 2024-04-19 09:35:54 +00:00 • committed by GitHub
parent 8b1b1f4982
commit 9958c81b79
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 271 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -122,6 +122,7 @@ Typically finetunes of the base models below are supported as well.
- [x] [Command-R](https://huggingface.co/CohereForAI/c4ai-command-r-v01)
- [x] [SEA-LION](https://huggingface.co/models?search=sea-lion)
- [x] [GritLM-7B](https://huggingface.co/GritLM/GritLM-7B) + [GritLM-8x7B](https://huggingface.co/GritLM/GritLM-8x7B)
- [x] [OLMo](https://allenai.org/olmo)
(instructions for supporting more models: [HOWTO-add-model.md](./docs/HOWTO-add-model.md))