| datasets: | |
| - tom-jerry-123/Physical-AI-AV-US | |
| base_model: | |
| - Qwen/Qwen3-VL-4B-Thinking | |
| Trained on 1000 steps from the `Physical-AI-AV-US' dataset. Observing the first 37 shards in the data. |
| datasets: | |
| - tom-jerry-123/Physical-AI-AV-US | |
| base_model: | |
| - Qwen/Qwen3-VL-4B-Thinking | |
| Trained on 1000 steps from the `Physical-AI-AV-US' dataset. Observing the first 37 shards in the data. |