Unify model card for both checkpoints

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: other
 language:
 - en
 tags:
@@ -8,17 +8,16 @@ tags:
 - multimodal
 - multi-object
 - pointllm
+- modelnet40
 pipeline_tag: text-generation
 ---
 
-# Multi-3DLLM
+# Multi-3DLLM Checkpoints
 
-Multi-3DLLM is the released checkpoint for BeyondSingleObject: Learning 3D
-Relations with Large Language Models. It extends the PointLLM-style 3D LLM
-interface to multiple point-cloud inputs and is intended for MO3D, Shape
-Mating, and Change Captioning experiments.
+This repository hosts the released BeyondSingleObject checkpoints:
 
-## Usage
+- `multi-3dllm/`: MO3D, Shape Mating, and Change Captioning
+- `multi-3dllm-classification/`: ModelNet40 zero-shot classification
 
 Use the code and scripts from:
 
@@ -26,15 +25,46 @@ Use the code and scripts from:
 https://github.com/KohsukeIde/BeyondSingleObject
 ```
 
+## Download
+
+```bash
+huggingface-cli download idekoh/Multi-3DLLM multi-3dllm --local-dir checkpoints/multi-3dllm
+huggingface-cli download idekoh/Multi-3DLLM multi-3dllm-classification --local-dir checkpoints/multi-3dllm-classification
+```
+
 Expected local layout:
 
 ```text
-checkpoints/multi-3dllm/
+checkpoints/
+├── multi-3dllm/
+└── multi-3dllm-classification/
 data/
 ```
 
-Example inference commands are provided in `scripts/eval/infer.sh`, and
-LLM-based evaluation wrappers are provided in `scripts/eval/eval_llm.sh`.
+## Usage
+
+Example inference and LLM-based evaluation:
+
+```bash
+MODEL_PATH=checkpoints/multi-3dllm \
+OUTPUT_DIR=outputs/infer \
+scripts/eval/infer.sh
+```
+
+ModelNet40 classification:
+
+```bash
+MODEL_PATH=checkpoints/multi-3dllm-classification \
+OUTPUT_DIR=outputs/modelnet40_eval \
+LIMIT=0 \
+PROMPT_MODE=paper \
+NUM_OBJECTS=1 \
+TARGET_POSITION=1 \
+scripts/eval/eval_modelnet.sh
+```
+
+Repeat `(NUM_OBJECTS, TARGET_POSITION) = (1,1), (2,1), (2,2), (3,1), (3,2),
+(3,3)` for the full table.
 
 ## Notes
 
@@ -43,6 +73,15 @@ judge model and prompt configuration. Use the released evaluation scripts for
 reproducible comparisons, and report the exact judge configuration together
 with the checkpoint.
 
+## License
+
+These checkpoints are built with the BeyondSingleObject codebase and use
+PointLLM-style initialization and data. They may inherit terms from upstream
+model, code, and dataset components, including PointLLM, Vicuna/Llama,
+Objaverse/Cap3D, ShapeTalk, Thingi10K, Neural Shape Mating, and ModelNet40.
+Please check the corresponding upstream licenses before redistribution or
+commercial use.
+
 ## Citation
 
 ```bibtex