Llama.cpp conversion fail, ffn_gate.weight not found

by Sciumo - opened Mar 6

Mar 6

main branch pulled today from llama.cpp
convert.py to fp16

llama_model_load: error loading model: create_tensor: tensor 'blk.0.ffn_gate.weight' not found

Cognitive Computations org Mar 6

shrug sounds like a bug in llama.cpp

Mar 9

use convert-hf-to-ggml.py

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

Tap or paste here to upload images

· Sign up or log in to comment