wassname/alpaca_convert
1
0
Fork 0
mirror of https://github.com/wassname/alpaca_convert.git synced 2026-06-27 17:47:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

git clone script working

Browse Source
This commit is contained in:
deep1
2023-04-22 18:42:01 +08:00
parent ba547ccb70
commit e4c04daadf
6 changed files with 35 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mjc_notes.md
+4 -4
View File
@@ -33,10 +33,10 @@ pip install git+https://github.com/sterlind/GPTQ-for-LLaMa.git@lora_4bit
```sh
# # base models.... FIXME
python scripts/download-model.py decapoda-research/llama-7b-hf
python scripts/download-model.py decapoda-research/llama-13b-hf
python scripts/download-model.py decapoda-research/llama-30b-hf
python scripts/download-model.py decapoda-research/llama-65b-hf
python scripts/clone-model.py decapoda-research/llama-7b-hf
python scripts/clone-model.py decapoda-research/llama-13b-hf
python scripts/clone-model.py decapoda-research/llama-30b-hf
python scripts/clone-model.py decapoda-research/llama-65b-hf
# oh! you need to replace LLaMATokenizer with LlamaTokenizer in all model json files
# download loras