Instructions to use anonymous-abc123/UniPhysGen-1.7B-Object with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anonymous-abc123/UniPhysGen-1.7B-Object with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="anonymous-abc123/UniPhysGen-1.7B-Object") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("anonymous-abc123/UniPhysGen-1.7B-Object", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use anonymous-abc123/UniPhysGen-1.7B-Object with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "anonymous-abc123/UniPhysGen-1.7B-Object" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anonymous-abc123/UniPhysGen-1.7B-Object", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/anonymous-abc123/UniPhysGen-1.7B-Object
- SGLang
How to use anonymous-abc123/UniPhysGen-1.7B-Object with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "anonymous-abc123/UniPhysGen-1.7B-Object" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anonymous-abc123/UniPhysGen-1.7B-Object", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "anonymous-abc123/UniPhysGen-1.7B-Object" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anonymous-abc123/UniPhysGen-1.7B-Object", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use anonymous-abc123/UniPhysGen-1.7B-Object with Docker Model Runner:
docker model run hf.co/anonymous-abc123/UniPhysGen-1.7B-Object
1.7B Object-Level Physics Checkpoint
Given a full-object point cloud, this checkpoint predicts object identity, category, dimensions, and mass. It does not require a target-part point cloud.
Model details
| Item | Value |
|---|---|
| Internal task name | object_level |
| Required geometry | Object point cloud only |
| Training lineage | 1.7B initialization โ physical grounding โ object-level fine-tuning |
| Training data | To be announced |
| Evaluation data | To be announced |
| Tested Transformers version | 4.51.0 |
Inputs and outputs
The recommended point-cloud format is .npz with aligned arrays:
point float32 [N, 3]
color uint8 [N, 3]
normal float32 [N, 3]
The structured prediction is:
{
"object_name": "cabinet",
"category": "Furniture/Cabinet",
"volume": [80.0, 40.0, 120.0],
"mass": 35.0
}
volume stores [length, width, height] in centimeters. mass is expressed
in kilograms.
Installation
Set CODE_REPO_URL to the URL of the anonymous source code repository.
git clone "$CODE_REPO_URL" source
cd source
python -m pip install -e .
bash scripts/install_cuda_extensions.sh
The model uses a custom Transformers architecture. Install the accompanying source code before
loading the checkpoint; a generic transformers.pipeline is not supported.
Inference
Replace /path/to/checkpoint with the local checkpoint directory.
CUDA_VISIBLE_DEVICES=0 python inference_batch_intrinsic_physics_object.py \
--model_path /path/to/checkpoint \
--object_pcd examples/object.npz \
--output outputs/intrinsic_physics_object.json
For batch inference, pass a JSON list with --input_json. No --part_pcd
argument is needed for this task.
Evaluation
python -m eval intrinsic_physics_object PREDICTIONS \
--output intrinsic_physics_object_metrics.json
Benchmark results are pending.
Intended use and limitations
This checkpoint is intended for research on object-level physical grounding and for proposing approximate object metadata for downstream simulation. Predicted dimensions and mass are estimates, not calibrated measurements.
Performance may degrade for incomplete scans, incorrect scale, sparse or noisy point clouds, unusual materials, composite objects, or categories outside the training distribution. Validate predictions before using them in robotics, safety-critical systems, or engineering workflows.
License
The model weights are released under the Creative Commons Attribution-NonCommercial 4.0 International license. Commercial use is not permitted under this license. The accompanying source code is licensed separately under Apache-2.0. See the included license for Qwen3 and Sonata attribution.
- Downloads last month
- -