pepijn223 HF Staff reach-vb HF Staff commited on
Commit
b60fb2c
·
verified ·
1 Parent(s): fabdefa

Add Robotics tag and metadata (#1)

Browse files

- Add Robotics tag and metadata (fc590bc8a5f7864c29e3ed8c8c001cff9aeb0629)


Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +47 -0
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lerobot/smolvla_base
3
+ library_name: lerobot
4
+ license: apache-2.0
5
+ model_name: smolvla
6
+ pipeline_tag: robotics
7
+ tags:
8
+ - robotics
9
+ - smolvla
10
+ ---
11
+
12
+ # Model Card for smolvla
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+ [SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
18
+
19
+
20
+ This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
21
+ See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
22
+
23
+ ---
24
+
25
+ ## How to Get Started with the Model
26
+
27
+ For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
28
+ Below is the short version on how to train and run inference/eval:
29
+
30
+ ### 1 Train from scratch
31
+
32
+ ```bash
33
+ python lerobot/scripts/train.py --dataset.repo_id=${HF_USER}/<dataset> --policy.type=act --output_dir=outputs/train/<desired_policy_repo_id> --job_name=lerobot_training --policy.device=cuda --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
34
+ --wandb.enable=true
35
+ ```
36
+
37
+ *Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`.*
38
+
39
+ ### 2 Evaluate the policy
40
+
41
+ ```bash
42
+ python -m lerobot.record --robot.type=so100_follower --dataset.repo_id=<hf_user>/eval_<dataset> --policy.path=<hf_user>/<desired_policy_repo_id> --episodes=10
43
+ ```
44
+
45
+ Prefix the dataset repo with **eval_** and supply `--policy.path` pointing to a local or hub checkpoint.
46
+
47
+ ---