How to use TheBloke/LLongMA-2-7B-GGML with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/LLongMA-2-7B-GGML", dtype="auto")
Do I properly understand it?If yes then under llama.cpp I just need --ctx-size 8186 ?
I'd say use-c 8192 --rope-freq-base 10000 --rope-freq-scale 0.5"As TheBloke wrote.
Ohh I see right now ... thanks
· Sign up or log in to comment