Add library_name, pipeline_tag and set inference to true

This PR adds the `library_name` tag, enabling the "how to use" button. It also adds a correct pipeline tag for this model, ensuring it can be found
at https://huggingface.co/models?pipeline_tag=text-to-video. It also enables the inference flag.

README.md

@@ -1,13 +1,15 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
+library_name: diffusers
+pipeline_tag: text-to-video
 tags:
-  - cogvideox
-  - video-generation
-  - thudm
-  - text-to-video
-inference: false
+- cogvideox
+- video-generation
+- thudm
+- text-to-video
+inference: true
 ---
 
 # CogVideoX-2B
@@ -180,7 +182,7 @@ pipe.vae.enable_tiling()
 + The 2B model is trained with `FP16` precision, and the 5B model is trained with `BF16` precision. We recommend using
   the precision the model was trained with for inference.
 + [PytorchAO](https://github.com/pytorch/ao) and [Optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be
-  used to quantize the text encoder, Transformer, and VAE modules to reduce CogVideoX's memory requirements. This makes
+  used to quantize the text encoder, transformer, and VAE modules to reduce CogVideoX's memory requirements. This makes
   it possible to run the model on a free T4 Colab or GPUs with smaller VRAM! It is also worth noting that TorchAO
   quantization is fully compatible with `torch.compile`, which can significantly improve inference speed. `FP8`
   precision must be used on devices with `NVIDIA H100` or above, which requires installing