h2oai

/

h2ogpt-16k-codellama-7b-python

like 0

Hello, i get error mismatch sizes when running this model and other h2ogpt. Do you have any solution? ignore mismatch = true does not work

RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:
size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([32000, 4096]) from checkpoint, the shape in current model is torch.Size([32016, 4096]).
size mismatch for lm_head.weight: copying a param with shape torch.Size([32000, 4096]) from checkpoint, the shape in current model is torch.Size([32016, 4096]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.

Thank you