ggml-org/gguf-my-repo · AttributeError: module 'torch' has no attribute 'uint64' when trying to convert fine-tuned model to GGUF format.

For the past day, i have been getting an attribute error message whenever I try converting a fine-tuned model I trained to GGUF format. I even tried converting a model that I was able to previously successfully convert to GUUF format to use in ollama, but I am getting the same error. Is there any way to fix this? Thank you.

Here is the full error message:

Error converting to fp16: Traceback (most recent call last):
File "/home/user/app/./llama.cpp/convert_hf_to_gguf.py", line 19, in
from transformers import AutoConfig
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/init.py", line 27, in
from . import dependency_versions_check
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/dependency_versions_check.py", line 16, in
from .utils.versions import require_version, require_version_core
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/utils/init.py", line 24, in
from .auto_docstring import (
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/utils/auto_docstring.py", line 30, in
from .generic import ModelOutput
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/utils/generic.py", line 55, in
from ..model_debugging_utils import model_addition_debugger_context
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/transformers/model_debugging_utils.py", line 30, in
from safetensors.torch import save_file
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/safetensors/torch.py", line 439, in
torch.uint64: 8,
^^^^^^^^^^^^
File "/home/user/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torch/init.py", line 1938, in getattr
raise AttributeError(f"module '{name}' has no attribute '{name}'")
AttributeError: module 'torch' has no attribute 'uint64'