The LLaMA PR has been merged into transformers

https://github.com/huggingface/transformers/pull/21955

The tokenizer class has been changed from

"LLaMATokenizer"

to

"LlamaTokenizer"

It is necessary to edit this change in every tokenizer_config.json
that you had for LLaMA so far.

requirements.txt

@@ -9,4 +9,4 @@ rwkv==0.4.2
 safetensors==0.3.0
 sentencepiece
 tqdm
-git+https://github.com/zphang/transformers.git@68d640f7c368bcaaaecfc678f11908ebbd3d6176
+git+https://github.com/huggingface/transformers