add missing dependency to train with LlamaTokenizer
This commit is contained in:
@@ -2,6 +2,7 @@ torch
|
|||||||
accelerate
|
accelerate
|
||||||
bitsandbytes
|
bitsandbytes
|
||||||
datasets
|
datasets
|
||||||
|
sentencepiece
|
||||||
git+https://github.com/huggingface/transformers.git
|
git+https://github.com/huggingface/transformers.git
|
||||||
git+https://github.com/sterlind/GPTQ-for-LLaMa.git@lora_4bit
|
git+https://github.com/sterlind/GPTQ-for-LLaMa.git@lora_4bit
|
||||||
git+https://github.com/sterlind/peft.git
|
git+https://github.com/sterlind/peft.git
|
||||||
|
|||||||
Reference in New Issue
Block a user