Q

[lxd1010]

I would like to know which large model you used for the evaluation. I have downloaded Qwen2.5-7B-Instruct, and do I need to download an additional vision encoder separately? Below is the result of my error report:

Inference checkpoints/Qwen2.5-7B-Instruct

Please install pyav to use video processing functions.

/opt/conda/lib/python3.10/site-packages/timm/models/layers/init.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers

warnings.warn(f"Importing from {name} is deprecated, please import via timm.layers", FutureWarning)

/lxd/third_party/mmdetection3d_1_0_0rc6/mmdet3d/core/evaluation/kitti_utils/eval.py:10: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.

def get_thresholds(scores: np.ndarray, num_gt, num_sample_pts=41):

[2026-01-16 02:14:55,817] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)

Starting inference of planning-oriented VLM...

Loading model with DeepSpeed...

Rank 0: Loaded LLaVA model: checkpoints/Qwen2.5-7B-Instruct

You are using a model of type qwen2 to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.

Rank 0: Overwriting config with {'image_aspect_ratio': 'pad', 'vision_tower_test_mode': True}

Loading checkpoint shards: 100%|██████████| 4/4 [00:09<00:00, 2.29s/it]

Rank 0: Model Class: LlavaQwenForCausalLM

Traceback (most recent call last):

File "/lxd/drivevla/inference_drivevla.py", line 360, in

main()

File "/lxd/drivevla/inference_drivevla.py", line 353, in main

inference_planning_oriented_vlm(args)

File "/lxd/drivevla/inference_drivevla.py", line 172, in inference_planning_oriented_vlm

tokenizer, model_engine, image_processor, context_len = load_model_with_deepspeed(args, device)

File "/lxd/drivevla/inference_drivevla.py", line 58, in load_model_with_deepspeed

tokenizer, model, image_processor, context_len = load_pretrained_model(

File "/lxd/llava/model/builder.py", line 313, in load_pretrained_model

if not vision_tower.is_loaded:

AttributeError: 'NoneType' object has no attribute 'is_loaded'

[2026-01-16 02:15:08,841] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 144) of binary: /opt/conda/bin/python

Traceback (most recent call last):

File "/opt/conda/bin/torchrun", line 33, in

sys.exit(load_entry_point('torch==2.1.2', 'console_scripts', 'torchrun')())

File "/opt/conda/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper

return f(*args, **kwargs)

File "/opt/conda/lib/python3.10/site-packages/torch/distributed/run.py", line 806, in main

run(args)

File "/opt/conda/lib/python3.10/site-packages/torch/distributed/run.py", line 797, in run

elastic_launch(

File "/opt/conda/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in call

return launch_agent(self._config, self._entrypoint, list(args))

File "/opt/conda/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent

raise ChildFailedError(

torch.distributed.elastic.multiprocessing.errors.ChildFailedError: