google / google/magika

gguf files aren't recognized

Open
#1,430 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Rust
Stars
18.6k
Forks
1.2k
Avg merge
3d 12h
Merged PRs (30d)
20

Description

```
$ magika moondream2-text-model-f16.gguf
/disks/samsung-4TB-A/AI-models/moondream2-text-model-f16.gguf: Unknown binary data (unknown) [Low-confidence model best-guess: Pytorch storage file (application), score=0.327]
$ magika grammar_error_correcter_v1.gguf
/disks/samsung-4TB-A/AI-models/grammar_error_correcter_v1.gguf: Unknown binary data (unknown) [Low-confidence model best-guess: Microsoft Cabinet archive data (archive), score=0.299]
$ magika WizardLM-2-7B.Q5_K_M.gguf
/disks/samsung-4TB-A/AI-models/WizardLM-2-7B.Q5_K_M.gguf: Unknown binary data (unknown) [Low-confidence model best-guess: Numpy Array (archive), score=0.320]
```

Contributor guide

Open the contributing guide

Research direction

Start by reproducing the reported results with the three .gguf files using the magika command shown. Trace the file-type detection path for unknown binary data and identify how a GGUF classification would be represented; done means these files are recognized consistently with an appropriate type and confidence.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.