Unable to finetune using Llama-Factory QLORA.
#8
by
Riobener
- opened
Hello, have tried to finetune this model. After that I exported the result and tried to run it in ollama and got this error:
Error: llama runner process has terminated: error loading model: check_tensor_dims: tensor 'token_embd.weight' has wrong shape; expected 4096, 128257, got 4096, 128256, 1, 1
I can't figure it out why does it happens. Thx in advance