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