Llama.cpp conversion fail, ffn_gate.weight not found

#4
by Sciumo - opened

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

shrug sounds like a bug in llama.cpp

use convert-hf-to-ggml.py

Sign up or log in to comment