-
Notifications
You must be signed in to change notification settings - Fork 12.4k
Closed
Labels
bugSomething isn't workingSomething isn't workinglow severityUsed to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
Description
What happened?
The script convert_hf_to_gguf.py does not perform a sanity check on the completeness of the model files. We encountered an issue where one of the models we downloaded was incomplete (specifically, a safesensors file was missing). Despite this, convert_hf_to_gguf.py proceeded with the conversion without generating any errors or warnings.
Expected Behavior: The script should validate that all required files are present before converting. Since Hugging Face downloads are organized with sequence and total files (e.g., model-00001-of-00002), it should be easy to validate.
Steps to Reproduce:
- Download a model from HF and delete one of the safesensors file.
- Run convert_hf_to_gguf.py on the incomplete set.
- the script completes without any indication of missing files.
Name and Version
version: 3631 (7d787ed)
built with cc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-22) for x86_64-redhat-linux
What operating system are you seeing the problem on?
Linux
Relevant log output
No response
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't workinglow severityUsed to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)