huangyanpei/VLA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
vincentccc
2025-09-08 22:26:19 +08:00
parent ff1feb611f
commit 64b41cc4f6
2 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -76,10 +76,16 @@ Training script path configuration
- Robot DOF configuration - Robot DOF configuration
- Training hyperparameters - Training hyperparameters
Download the Flow/FAST pretrained model and run:
```bash ```bash
bash ./workspace/lerobot_example/run.sh bash ./workspace/lerobot_example/run.sh
``` ```
To fine-tune using the FAST tokenizer, please download the repository and update the `action_tokenizer_path`. Make sure to set `use_fast_tokenizer` to `true`:
```bash
git clone https://huggingface.co/physical-intelligence/fast
```
## Inference ## Inference
For model inference, please refer to: For model inference, please refer to:
workspace/lerobot_example/config_qact.yml
+2
View File
@@ -6,6 +6,8 @@ log_name: "robotic_training"
log_project: "vla_training" log_project: "vla_training"
model_type: qwen2_5 model_type: qwen2_5
pretrained_qwen_vl_path: "/path/to/qwen_vl_model/" pretrained_qwen_vl_path: "/path/to/qwen_vl_model/"
# whether to enable fast tokenizer
use_fast_tokenizer: false
action_tokenizer_path: "/path/to/fast/" action_tokenizer_path: "/path/to/fast/"
save_path: "/path/to/workspace/" save_path: "/path/to/workspace/"