Fix minor issues

4D-R1-GRPO-MP/README.md

@@ -1,9 +1,9 @@
-# 4D-R1-GRPO-MP
-
-4D-R1 LoRA adapter corresponding to **GRPO (mixed-precision)** in the paper.
-
-Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation. This directory contains adapter weights and configuration, not a standalone base model.
-
-LoRA rank: 16. Target modules: q, k, v, o.
-
-MP denotes mixed-precision training.
+# 4D-R1-GRPO-MP
+
+4D-R1 LoRA adapter corresponding to **GRPO (mixed-precision)** in the paper.
+
+Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation.
+
+LoRA rank: 16. Target modules: q, k, v, o.
+
+MP denotes mixed-precision training.

4D-R1-GRPO/README.md

@@ -1,7 +1,7 @@
-# 4D-R1-GRPO
-
-4D-R1 LoRA adapter corresponding to **GRPO** in the paper.
-
-Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation. This directory contains adapter weights and configuration, not a standalone base model.
-
-LoRA rank: 16. Target modules: q, k, v, o.
+# 4D-R1-GRPO
+
+4D-R1 LoRA adapter corresponding to **GRPO** in the paper.
+
+Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation.
+
+LoRA rank: 16. Target modules: q, k, v, o.

4D-R1-NFT-MP/README.md

@@ -1,9 +1,9 @@
-# 4D-R1-NFT-MP
-
-4D-R1 LoRA adapter corresponding to **NFT (mixed-precision)** in the paper.
-
-Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation. This directory contains adapter weights and configuration, not a standalone base model.
-
-LoRA rank: 16. Target modules: q, k, v, o.
-
-MP denotes mixed-precision training.
+# 4D-R1-NFT-MP
+
+4D-R1 LoRA adapter corresponding to **NFT (mixed-precision)** in the paper.
+
+Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation.
+
+LoRA rank: 16. Target modules: q, k, v, o.
+
+MP denotes mixed-precision training.

4D-R1-NFT/README.md

@@ -1,7 +1,7 @@
-# 4D-R1-NFT
-
-4D-R1 LoRA adapter corresponding to **NFT** in the paper.
-
-Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation. This directory contains adapter weights and configuration, not a standalone base model.
-
-LoRA rank: 16. Target modules: q, k, v, o.
+# 4D-R1-NFT
+
+4D-R1 LoRA adapter corresponding to **NFT** in the paper.
+
+Use this adapter with the VerseCrafter base model and the 4D-R1 inference implementation.
+
+LoRA rank: 16. Target modules: q, k, v, o.

README.md

@@ -1,28 +1,28 @@
----
-library_name: peft
-tags:
-- lora
-- video-generation
-- motion-control
----
-
-# 4D-R1
-
-LoRA adapters for 4D-R1, a reinforcement post-training framework for motion control and efficient video generation built on VerseCrafter.
-
-| Directory | Paper model |
-|---|---|
-| `4D-R1-GRPO` | GRPO |
-| `4D-R1-NFT` | NFT |
-| `4D-R1-GRPO-MP` | GRPO (mixed-precision) |
-| `4D-R1-NFT-MP` | NFT (mixed-precision) |
-
-Each directory contains `adapter_model.safetensors` and `adapter_config.json`. The adapters use LoRA rank 16 on the q, k, v, and o projections.
-
-These are LoRA adapters, not standalone full-model checkpoints. Inference requires the VerseCrafter base model, its companion components, and the compatible 4D-R1 inference implementation. Base-model weights are not included in this repository.
-
-MP denotes mixed-precision training.
-
-The corresponding paper rows are GRPO, NFT, GRPO (mixed-precision), and NFT (mixed-precision).
-
-`SHA256SUMS` provides checksums for the adapter weights and configuration files.
+---
+library_name: peft
+tags:
+- lora
+- video-generation
+- motion-control
+---
+
+# 4D-R1
+
+LoRA adapters for 4D-R1, a reinforcement post-training framework for motion control and efficient video generation built on VerseCrafter.
+
+| Directory | Paper model |
+|---|---|
+| `4D-R1-GRPO` | GRPO |
+| `4D-R1-NFT` | NFT |
+| `4D-R1-GRPO-MP` | GRPO (mixed-precision) |
+| `4D-R1-NFT-MP` | NFT (mixed-precision) |
+
+Each directory contains `adapter_model.safetensors` and `adapter_config.json`. The adapters use LoRA rank 16 on the q, k, v, and o projections.
+
+Inference requires the VerseCrafter base model, its companion components, and the compatible 4D-R1 inference implementation.
+
+MP denotes mixed-precision training.
+
+The corresponding paper rows are GRPO, NFT, GRPO (mixed-precision), and NFT (mixed-precision).
+
+`SHA256SUMS` provides checksums for the adapter weights and configuration files.