Robotics
Safetensors
PyTorch
English
alpamayo2_edge
alpamayo
autonomous-driving
vision-language-action
hatsoff2you commited on
Commit
5aaf394
·
verified ·
1 Parent(s): aaaa32c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -23,13 +23,13 @@ Alpamayo 2 Edge is a vision-language-action model for navigation-conditioned dri
23
 
24
  ### License/Terms of Use:
25
 
26
- **Model weights:** The repository metadata lists `openmdw-1.1`. **TBD — confirm the model license and applicable access/use terms.**
27
 
28
  **Source code:** See the [code repository license](https://github.com/NVlabs/alpamayo2-edge/blob/ga-release/LICENSE). Source-code licensing does not establish the license for these model weights.
29
 
30
  ### Deployment Geography:
31
 
32
- **TBD — supported regions and any geographic restrictions.**
33
 
34
  ### Use Case:
35
 
@@ -39,7 +39,7 @@ Navigation-conditioned driving reasoning and trajectory prediction for autonomou
39
 
40
  ### Release Date:
41
 
42
- **Hugging Face:** TBD, at [nvidia/Alpamayo2-Edge](https://huggingface.co/nvidia/Alpamayo2-Edge).
43
 
44
  ## Model Architecture:
45
 
@@ -146,9 +146,8 @@ This checkpoint uses the Cosmos3-Edge vision-language backbone and the course-he
146
 
147
  **Acceleration Engine:** PyTorch and Hugging Face Transformers.
148
 
149
- **Hardware Requirements (GPU Architecture, Model):** TBD — minimum GPU memory, validated devices, and measured runtime configuration.
150
 
151
- **Latency, throughput, and peak memory:** TBD.
152
 
153
  **Sampling:** Reasoning generation is followed by ten Euler diffusion steps by default. `--num-traj-sets` controls independently generated reasoning continuations; `--num-traj-samples` controls trajectories per continuation.
154
 
 
23
 
24
  ### License/Terms of Use:
25
 
26
+ **Model weights:** The model weights are released under the [OpenMDW-1.1](https://openmdw.ai/license/1-1/) license.
27
 
28
  **Source code:** See the [code repository license](https://github.com/NVlabs/alpamayo2-edge/blob/ga-release/LICENSE). Source-code licensing does not establish the license for these model weights.
29
 
30
  ### Deployment Geography:
31
 
32
+ Global
33
 
34
  ### Use Case:
35
 
 
39
 
40
  ### Release Date:
41
 
42
+ **Hugging Face:** 11/10/2026, at [nvidia/Alpamayo2-Edge](https://huggingface.co/nvidia/Alpamayo2-Edge).
43
 
44
  ## Model Architecture:
45
 
 
146
 
147
  **Acceleration Engine:** PyTorch and Hugging Face Transformers.
148
 
149
+ **Hardware Requirements (GPU Architecture, Model):** 16GB minimum GPU memory, validated devices (Thor-U), and measured runtime configuration (6 trajectories).
150
 
 
151
 
152
  **Sampling:** Reasoning generation is followed by ten Euler diffusion steps by default. `--num-traj-sets` controls independently generated reasoning continuations; `--num-traj-samples` controls trajectories per continuation.
153