Instructions to use dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir CogVideoX-Fun-V1.5-5b-InP-mlx dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
metadata
library_name: mlx
license: apache-2.0
base_model: alibaba-pai/CogVideoX-Fun-V1.5-5b-InP
tags:
- mlx
- mlx-forge
- apple-silicon
- safetensors
dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx
MLX format conversion of alibaba-pai/CogVideoX-Fun-V1.5-5b-InP.
Converted with mlx-forge.
Usage
These weights can be used with VideoX-Fun-mlx.
Related Projects
- VideoX-Fun-mlx (inference code): https://github.com/dgrauet/VideoX-Fun-mlx
- mlx-forge (conversion tool): https://github.com/dgrauet/mlx-forge
- mlx-arsenal (MLX utilities): https://github.com/dgrauet/mlx-arsenal
- q8 variant: https://huggingface.co/dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx-q8
- q4 variant: https://huggingface.co/dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx-q4
Files
config.json(2.78 KB)configuration.json(56.00 B)model_index.json(411.00 B)scheduler_scheduler_config.json(482.00 B)split_model.json(379.00 B)text_encoder.safetensors(8.87 GB)text_encoder_config.json(782.00 B)tokenizer_added_tokens.json(2.53 KB)tokenizer_special_tokens_map.json(2.48 KB)tokenizer_tokenizer_config.json(20.13 KB)transformer.safetensors(10.38 GB)transformer_config.json(887.00 B)vae.safetensors(411.25 MB)vae_config.json(839.00 B)