schihei/llama2.c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

todos update

Browse Source
This commit is contained in:
Andrej Karpathy
2023-08-20 17:02:22 +00:00
parent f3db92a2dc
commit 13dcee493a
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -308,11 +308,11 @@ If your candidate PRs have elements of these it doesn't mean they won't get merg
## unsorted todos ## unsorted todos
- make it easier to add a new dataset with not too much pain - delete the export_meta_llama_bin.py and export_meta_llama_hf_bin.py files. instead, import both of these into a proper model.py Transformer instance, and then export using the export script as usual.
- should calculate freq_cis online in the script run.c instead of loading them - migrate the code to work with the new versions export and deprecate the original .bin files
- int4/8 quantization
- export the model in a more sensible output format with a proper header, etc.
- support Llama 2 7B Chat models and tune run.c to Chat UI/UX - support Llama 2 7B Chat models and tune run.c to Chat UI/UX
- make it easier to add a new dataset with not too much pain
- int8 quantization
- llama2.cu investigate and merge - llama2.cu investigate and merge
- (LoRA) finetuning and export of Llama 2 models - (LoRA) finetuning and export of Llama 2 models