preview_model / README.md
ccccsc's picture
Add files using upload-large-folder tool
24e3a25 verified
|
Raw History Blame Contribute Delete
1.68 kB
# Preview Model Weights
This directory contains the local weights required by the Preview Model.
## Weight Mapping
| Component | Local path | Description |
| --- | --- | --- |
| Video generation model (VGen) | `checkpoints/diffusion_pytorch_model.bin` | Main video diffusion model. |
| Action Expert | `checkpoints/action_model/diffusion_pytorch_model.bin` | Action prediction model. |
| VAE | `vae/diffusion_pytorch_model.safetensors` | Video latent encoder and decoder. |
| VAE latent statistics | `vae/latent_stats.pth` | Latent normalization statistics used by the VAE. |
| Qwen3.5 VLM | [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) | Vision-language model used for instruction and image conditioning. |
The `config.json` files next to each model define the corresponding model
architecture.
## Expected Layout
```text
preview_model/
β”œβ”€β”€ checkpoints/
β”‚ β”œβ”€β”€ config.json
β”‚ β”œβ”€β”€ diffusion_pytorch_model.bin
β”‚ └── action_model/
β”‚ β”œβ”€β”€ config.json
β”‚ └── diffusion_pytorch_model.bin
β”œβ”€β”€ vae/
β”‚ β”œβ”€β”€ config.json
β”‚ β”œβ”€β”€ diffusion_pytorch_model.safetensors
β”‚ └── latent_stats.pth
└── stats.json
```
`stats.json` contains the state and action normalization statistics used during
policy inference.
## Runtime Paths
Use `preview_model/checkpoints` as the `CKPT` directory, use
`preview_model/vae` as the configured VAE path, and set the VAE statistics path
to `preview_model/vae/latent_stats.pth`. Download Qwen3.5-2B from the link above
and set `vlm_model_id` to its local directory or directly to
`Qwen/Qwen3.5-2B` when Hugging Face downloads are available.