shubh-gupta-ai commited on
Commit
98d56d8
·
verified ·
1 Parent(s): 698e955

Set license to CC BY-NC-SA 4.0

Browse files
Files changed (1) hide show
  1. README.md +11 -8
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: apache-2.0
3
  base_model: Qwen/Qwen2.5-VL-3B-Instruct
4
  pipeline_tag: image-text-to-text
5
  library_name: transformers
@@ -13,13 +13,13 @@ tags:
13
 
14
  # NoRD-Base: No Reasoning for Driving (SFT only)
15
 
16
- **CVPR 2026** | [arXiv](https://arxiv.org/abs/2602.21172) | [Project Page](https://nord-vla-ai.github.io/) | [GitHub](https://github.com/Applied-Intuition-Open-Source/nord)
17
 
18
  *Ishaan Rawal · Shubh Gupta · Yihan Hu · Wei Zhan*
19
 
20
- This is the **SFT-only** checkpoint from the paper. [Qwen2.5-VL-3B](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
21
- supervised fine-tuned to directly predict driving trajectories as discrete tokens without
22
- chain-of-thought reasoning, using 3× fewer tokens than reasoning-based VLA baselines. This checkpoint
23
  is also the initialization used for the Dr. GRPO stage that produces the paper's main result.
24
 
25
  | Model | Training | NAVSIM PDMS |
@@ -29,9 +29,10 @@ is also the initialization used for the Dr. GRPO stage that produces the paper's
29
 
30
  ## Usage
31
 
32
- Install the [`nord`](https://github.com/Applied-Intuition-Open-Source/nord) client and serve with vLLM:
33
 
34
  ```bash
 
35
  vllm serve AppliedIntuitionResearch/nord-base --served-model-name qwen --dtype bfloat16 --port 8000
36
  ```
37
 
@@ -50,7 +51,7 @@ output = agent.predict(nord.NordInput(
50
  print(output.trajectory.shape) # (40, 3) — x, y, heading at 10 Hz, 4 seconds
51
  ```
52
 
53
- Full inference and NAVSIM evaluation instructions: [github.com/nord-vla-ai/nord](https://github.com/Applied-Intuition-Open-Source/nord).
54
 
55
  This repo bundles the K-Disc trajectory tokenizer vocab (`vocab.pkl`, 2048 clusters) used to
56
  decode the model's output tokens into `(x, y, heading)` trajectories.
@@ -68,4 +69,6 @@ decode the model's output tokens into `(x, y, heading)` trajectories.
68
 
69
  ## License
70
 
71
- Apache 2.0.
 
 
 
1
  ---
2
+ license: cc-by-nc-sa-4.0
3
  base_model: Qwen/Qwen2.5-VL-3B-Instruct
4
  pipeline_tag: image-text-to-text
5
  library_name: transformers
 
13
 
14
  # NoRD-Base: No Reasoning for Driving (SFT only)
15
 
16
+ **CVPR 2026** | [arXiv](https://arxiv.org/abs/2602.21172) | [Project Page](https://nord-vla-ai.github.io/) | [GitHub](https://github.com/nord-vla-ai/nord)
17
 
18
  *Ishaan Rawal · Shubh Gupta · Yihan Hu · Wei Zhan*
19
 
20
+ This is the **SFT-only ablation baseline** from the paper: [Qwen2.5-VL-3B](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
21
+ supervised fine-tuned to directly predict driving trajectories as discrete tokens — no
22
+ chain-of-thought reasoning, 3× fewer tokens than reasoning-based VLA baselines. This checkpoint
23
  is also the initialization used for the Dr. GRPO stage that produces the paper's main result.
24
 
25
  | Model | Training | NAVSIM PDMS |
 
29
 
30
  ## Usage
31
 
32
+ Install the [`nord`](https://github.com/nord-vla-ai/nord) client and serve with vLLM:
33
 
34
  ```bash
35
+ pip install "nord[serve]"
36
  vllm serve AppliedIntuitionResearch/nord-base --served-model-name qwen --dtype bfloat16 --port 8000
37
  ```
38
 
 
51
  print(output.trajectory.shape) # (40, 3) — x, y, heading at 10 Hz, 4 seconds
52
  ```
53
 
54
+ Full inference and NAVSIM evaluation instructions: [github.com/nord-vla-ai/nord](https://github.com/nord-vla-ai/nord).
55
 
56
  This repo bundles the K-Disc trajectory tokenizer vocab (`vocab.pkl`, 2048 clusters) used to
57
  decode the model's output tokens into `(x, y, heading)` trajectories.
 
69
 
70
  ## License
71
 
72
+ This checkpoint is released under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
73
+ (non-commercial). The `nord` inference client code is separately licensed under Apache 2.0 —
74
+ see [github.com/nord-vla-ai/nord](https://github.com/nord-vla-ai/nord).