How to use ZengXiangyu/Llama-2-13b-hici-16k-none with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZengXiangyu/Llama-2-13b-hici-16k-none", device_map="auto")
How to use ZengXiangyu/Llama-2-13b-hici-16k-none with PEFT:
Task type is invalid.
https://huggingface.co/ZengXiangyu/Llama-2-13b-hici-16k-none/resolve/main/tokenizer.json
hf download hf://ZengXiangyu/Llama-2-13b-hici-16k-none/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/ZengXiangyu/Llama-2-13b-hici-16k-none/resolve/main/tokenizer.json
