loading as llama model

by KnutJaegersberg - opened Sep 24, 2024

Sep 24, 2024

seems to load as DeciLMForCausalLM, is it possible to load it as llama for easy compatibility?

itlevy

NVIDIA org Sep 26, 2024

Sorry, our custom architecture is not supported by modeling_llama.py

KnutJaegersberg changed discussion status to closed Sep 26, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment