Refresh the card so its own manifest size line is current

Add the usage snippet, taken from the inference project's own README

Add the usage snippet, taken from the inference project's own README

Record the quantization group size in the manifest

Record the quantization group size in the manifest

Complete the card metadata: the quantization the recipe now declares

Complete the card metadata: the quantization the recipe now declares

Record the repo's sibling links in the manifest

Record the repo's sibling links in the manifest

Add missing T5 spiece.model (tokenizer was unusable without it)

docs: update mlx-ops reference to mlx-arsenal

Upload CogVideoX-Fun-V1.5-5b-InP MLX (int8, T5 bf16)

Upload MLX model via mlx-forge

initial commit