Ir para o conteúdo
ModelListadosExterno
Baixar

Ground3D LMM CAVQA 4B Joint

Fine-tuned Ground3D-LMM checkpoint for CA-VQA (paper Table 9 — generality beyond ScanNet), 3D+2D (point cloud + RGB views) setting. Reproduces the paper's Table-9 average (48).

TipoOtherVersãoPytorch modelBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
10,7 GB
Versão
vPytorch model
Atualizado
10 de out. de 2026
Fonte
Hugging Face

Descrição da fonte

Ground3D-LMM — CA-VQA (3D+2D)

Fine-tuned Ground3D-LMM checkpoint for CA-VQA (paper Table 9 — generality beyond ScanNet), 3D+2D (point cloud + RGB views) setting. Reproduces the paper's Table-9 average (~48).

Usage

CKPT=$(huggingface-cli download amolharsh/Ground3D-LMM-CAVQA-4B-Joint pytorch_model.pth)
# evaluate with the CA-VQA harness: infer_cavqa.py -> merge_preds.py -> evaluate_cavqa.py

Fontes

1 fonte
Hugging FacePrimárioVersão 4f6afd5c69ddde7f6da790e25d2269bfdf2cef21
huggingface.co/amolharsh/Ground3D-LMM-CAVQA-4B-Joint/tree/4f6afd5c69ddde7f6da790e25d2269bfdf2cef21

Verificado 10 de out.

Artefatos de modelo

1 artefato

pytorch_model.pth

pth · 10,7 GB · SHA-256 11547dfd419d…fa13 · Hugging Face

Download file

Trechos de fonte

2 trechos

--- license: apache-2.0 library_name: pytorch tags: - 3d - visual-question-answering - spatial-reasoning - ground3d-lmm --- # Ground3D-LMM — CA-VQA (3D+2D) Fine-tuned **Ground3D-LMM** checkpoint for **CA-VQA** (paper **Table 9** — generality beyond ScanNet), **3D+2D (point cloud + RGB views)** setting. Reproduces the paper's Table-9 average (~48). - **Checkpoint file:** `pytorch_model.pth` - **Code:** https://github.com/AmolHarsh/ground3d-lmm ## Usage ```bash CKPT=$(huggingface-cli download amolharsh/Ground3D-LMM-CAVQA-4B-Joint pytorch_model.pth) # evaluate with the CA-VQA harness: infer_cavqa.py -> merge_preds.py -> evaluate_cavqa.py ```

Source context: 0 downloads · 0 likes · Pipeline visual-question-answering · Library pytorch · Repo amolharsh/Ground3D-LMM-CAVQA-4B-Joint