Update checkpoint README

README.md

@@ -4,19 +4,19 @@ license: openrail
 
 # Micro-World 2.0
 
-Action-controlled causal world-model checkpoints. Micro-World 2.0 generates 352×640 video from a first frame, a text prompt, and keyboard/mouse actions. The distilled student denoises each chunk in 4 steps with `guidance_scale` 1.0.
+Action-controlled causal world-model checkpoints. Micro-World 2.0 generates 352×640 video from a first frame, a text prompt, and keyboard/mouse actions. The distilled student denoises each chunk in 4 steps.
 
-`causal-forcing-init` is our own initialization checkpoint, trained by us. It is not the official Causal-Forcing release. The Wan2.2-TI2V-5B base weights are not in this repository; download them from [Wan-AI/Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B).
+The Wan2.2-TI2V-5B base weights are not in this repository; download them from [Wan-AI/Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B).
 
 ## Checkpoints
 
 | Path | What it is |
 | --- | --- |
-| `causal-forcing-init/model.pt` | Our causal-forcing initialization. Loaded onto the Wan2.2 transformer before the LoRAs. |
+| `causal-forcing-init/model.pt` | Causal-forcing initialization. Loaded onto the Wan2.2 transformer before the LoRAs. |
 | `causal-lora/lora_diffusion_pytorch_model.safetensors` | Causal LoRA. Adapts the backbone to open-domain 352×640 video. |
 | `action/` | Action module. Inference reads `action_preprocess` and `action_adaLN_modulation` from this checkpoint. |
 | `dmd-lora/lora_diffusion_pytorch_model.safetensors` | DMD student LoRA used for 4-step generation. |
-| `light_vae/` | Optional TurboVAED decoder from [amd/HummingbirdXT](https://huggingface.co/amd/HummingbirdXT/tree/main/vae/wan22_v1_tiling_16_12). Faster decode with some loss of fidelity. Omit it to use the Wan VAE. |
+| `light_vae/` | Optional TurboVAED decoder from [amd/HummingbirdXT](https://huggingface.co/amd/HummingbirdXT/tree/main/vae/wan22_v1_tiling_16_12). Faster decode with few loss of fidelity. Omit it to use the Wan VAE. |
 
 ## Load order
 
@@ -26,6 +26,4 @@ Action-controlled causal world-model checkpoints. Micro-World 2.0 generates 352
 4. `action`
 5. `dmd-lora`
 
-Chunk size is 3, the local attention window is 21, and the sink size is 1.
-
 Training and inference code: [Micro-World](https://github.com/AMD-AGI/Micro-World).