starVLA/Qwen3-VL-4B-Instruct-Action
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: starVLA/Qwen3-VL-4B-Instruct-Action
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-16 12:47:13 +08:00
commit 191f715433
18 changed files with 38215 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md Normal file
View File

@@ -0,0 +1,8 @@
The key difference is that Qwen3-VL-4B-Instruct-Action extends the original tokenizer with an additional 2048 action tokens. Otherwise, it is identical to Qwen3-VL-4B-Instruct—no additional fine-tuning was applied.
To add these tokens, we used the script:
starVLA/model/modules/vlm/tools/add_qwen_special_tokens
The model simply expands the token codebook to accommodate action token embeddings, but the underlying VLM weights remain unchanged from the base Instruct model.