Image-to-3D
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
Multimodal-Large-Language-Model,mesh-generation
text-generation-inference
Instructions to use yejunliang23/ShapeLLM-7B-omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yejunliang23/ShapeLLM-7B-omni with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("yejunliang23/ShapeLLM-7B-omni") model = AutoModelForMultimodalLM.from_pretrained("yejunliang23/ShapeLLM-7B-omni", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from yejunliang23/ShapeLLM-7B-omni: direct link, hf CLI and curl.
- Browser
- Download file 14 MB
-
https://huggingface.co/yejunliang23/ShapeLLM-7B-omni/resolve/main/trainer_state.json
- Command line
-
hf download hf://yejunliang23/ShapeLLM-7B-omni/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/yejunliang23/ShapeLLM-7B-omni/resolve/main/trainer_state.json
14 MB
- Xet hash:
- 7125882e3618c9be83eec50ee62e95801b6ea830bd898d028f11a41e983d4a8a
- Size of remote file:
- 14 MB
- SHA256:
- bec894908ee52b8869a7a4e52d57cdfb65e5ad9960de15e1398ced415313bf54
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.