Fix deprecated float16/fp16 variant loading through new `version` API.

Hey CompVis 👋,

Your model repository seems to contain a [`fp16` branch](https://huggingface.co/CompVis/ldm-super-resolution-4x-openimages/tree/fp16) to load the model in float16 precision. Loading `fp16` versions from a branch instead of the main branch is deprecated and will eventually be forbidden. Instead, we strongly recommend to save `fp16` versions of the model under `.fp16.` version files directly on the 'main' branch as enabled through this PR.This PR makes sure that your model repository allows the user to correctly download float16 precision model weights by adding `fp16` model weights in both safetensors and PyTorch bin format:

```py
pipe = DiffusionPipeline.from_pretrained(CompVis/ldm-super-resolution-4x-openimages, torch_dtype=torch.float16, variant='fp16')
```

For more information please have a look at: https://huggingface.co/docs/diffusers/using-diffusers/loading#checkpoint-variants.
We made sure you that you can safely merge this pull request.

Best, the 🧨 Diffusers team.

unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f509b385172ff96df979b1ace76eef0d90c0762de56a22ca545dd7ede4ec78
+size 227370409

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b369482570c4a798a3522aacf94aee557305005aecaa96d34fb108d975de481f
+size 227280286

vqvae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800b11b7c0a3f1f447bdf76dc787d9021ab4858325fadf574e0228b2c2736527
+size 110726178

vqvae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e501d1cf3f08775380bf6a4676bdced4f1896963cb9c41db550631c6c9e71c
+size 110668188