Upload ordinary self-forcing step 600 EMA checkpoint from CD initialization

dcba1b2 verified 9 days ago

1.38 kB

---
pipeline_tag: text-to-video
tags:
  - omnimem
  - wan
  - video-generation
  - self-forcing
---
# self_forcing_from_cd
OmniMem ordinary self-forcing checkpoint initialized from CD-trained generator weights.
This release contains the **generator EMA weights at self-forcing training step 600**.
It is the initialization checkpoint used by [long_rolling_plain_from_cd](https://huggingface.co/omnimem/long_rolling_plain_from_cd).
## Checkpoint lineage
CD step-4500 EMA → ordinary self-forcing step-600 EMA → plain rolling training.
## Contents
- `config.json`
- Two `safetensors` weight shards and their index
- `SHA256SUMS` for payload integrity checking
The weights retain their original FP32 storage. The model configuration uses NSA top-12 block selection.
## Usage
Use compatible OmniMem code with `CausalWanNSAModel` and `CausalWanT2VPipeline`.
The Wan2.1 VAE, UMT5 text encoder, and tokenizer are separate required components.
```python
from omnimem.models.transformers.causal_wan_nsa_model import CausalWanNSAModel

model = CausalWanNSAModel.from_pretrained(
    "omnimem/self_forcing_from_cd"
)
```
The original checkpoint configuration is preserved unchanged. Its saved class name
records the training wrapper, and `_name_or_path` records the upstream CD initialization source.
The released payload is the **ordinary self-forcing step-600 EMA** checkpoint.

	---
	pipeline_tag: text-to-video
	tags:
	- omnimem
	- wan
	- video-generation
	- self-forcing
	---

	# self_forcing_from_cd

	OmniMem ordinary self-forcing checkpoint initialized from CD-trained generator weights.

	This release contains the generator EMA weights at self-forcing training step 600.
	It is the initialization checkpoint used by [long_rolling_plain_from_cd](https://huggingface.co/omnimem/long_rolling_plain_from_cd).

	## Checkpoint lineage

	CD step-4500 EMA → ordinary self-forcing step-600 EMA → plain rolling training.

	## Contents

	- `config.json`
	- Two `safetensors` weight shards and their index
	- `SHA256SUMS` for payload integrity checking

	The weights retain their original FP32 storage. The model configuration uses NSA top-12 block selection.

	## Usage

	Use compatible OmniMem code with `CausalWanNSAModel` and `CausalWanT2VPipeline`.
	The Wan2.1 VAE, UMT5 text encoder, and tokenizer are separate required components.

	```python
	from omnimem.models.transformers.causal_wan_nsa_model import CausalWanNSAModel

	model = CausalWanNSAModel.from_pretrained(
	"omnimem/self_forcing_from_cd"
	)
	```

	The original checkpoint configuration is preserved unchanged. Its saved class name
	records the training wrapper, and `_name_or_path` records the upstream CD initialization source.
	The released payload is the ordinary self-forcing step-600 EMA checkpoint.