Minecraft-Openha-Qwen2vl-7b-2509

✨ Highlights

This model is built on Qwen2-VL-7B-Instruct and introduces two key innovations:

  • Chain of Action (CoA): bridges reasoning and control by using abstracted actions as thoughts.
  • All-in-One training: unifies motion, grounding, and text actions into a single framework, enabling broad generalization beyond specialist agents.

πŸ’» Usage

You can download and use this model with:

python examples/rollout_openha.py \
    --output_mode text_action  \
    --vlm_client_mode hf \
    --system_message_tag text_action \
    --model_ips localhost --model_ports 11000 \
    --model_id minecraft-openha-qwen2vl-7b-2509 \
    --record_path "~/evaluate" \
    --max_steps_num 200 \
    --num_rollouts 8
Downloads last month
29
Safetensors
Model size
8.29B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for CraftJarvis/minecraft-openha-qwen2vl-7b-2509

Base model

Qwen/Qwen2-VL-7B
Finetuned
(453)
this model

Datasets used to train CraftJarvis/minecraft-openha-qwen2vl-7b-2509

Collection including CraftJarvis/minecraft-openha-qwen2vl-7b-2509