Skip converting .safetensors to .bin

[ysjprojects]

Addresses #1625

Tested it locally on Qwen2.5-0.5b and it appears to work fine.

[ysjprojects]

Hi, just checking if this PR will be pursued soon.

[gitguardian]

️✅ There are no secrets present in this pull request anymore.

If these secrets were true positive and are still valid, we highly recommend you to revoke them.
While these secrets were previously flagged, we no longer have a reference to the
specific commits where they were detected. Once a secret has been leaked into a git
repository, you should consider it compromised, even if it was deleted immediately.
Find here more information about risks.

---

^{_{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}}

[Andrei-Aksionov]

Hey @ysjprojects

Hi, just checking if this PR will be pursued soon.

Yeah, I checked the PR.
And butchered it a lil bit in the process 🙃

I don't see anything wrong with it.
It doesn't increase the peak memory consumption. Looks like _lazy_load loads data, but also keeps previously loaded one in memory. So no disadvantages in loading .safetensors data right away.
The benefit is, of course, that we don't need to do the conversion.

Good job 👍