hl-planner-simple-subgoal
LoRA adapter on Qwen3-VL-4B-Instruct for robot subgoal prediction from setup video + task goal.
- Base:
Qwen/Qwen3-VL-4B-Instruct - Adapter: LoRA (~132 MB safetensors)
- License: MIT
Inference env vars (required)
These MUST match training; setting them higher (or leaving the defaults) silently degrades quality.
export IMAGE_MAX_TOKEN_NUM=128
export VIDEO_MAX_TOKEN_NUM=128
export FPS_MAX_FRAMES=10
Use
Load via peft on top of Qwen3-VL with the env vars above set BEFORE
importing swift.llm / transformers.
- Downloads last month
- 36
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for bingaochen/hl-planner-simple-subgoal
Base model
Qwen/Qwen3-VL-4B-Instruct