Instructions to use suryadv/strive-kubric-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suryadv/strive-kubric-checkpoints with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="suryadv/strive-kubric-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("suryadv/strive-kubric-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use suryadv/strive-kubric-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suryadv/strive-kubric-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suryadv/strive-kubric-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/suryadv/strive-kubric-checkpoints

SGLang

How to use suryadv/strive-kubric-checkpoints 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 "suryadv/strive-kubric-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suryadv/strive-kubric-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "suryadv/strive-kubric-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suryadv/strive-kubric-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use suryadv/strive-kubric-checkpoints with Docker Model Runner:
```
docker model run hf.co/suryadv/strive-kubric-checkpoints
```

STRIVE Kubric checkpoints

This repository contains the three merged checkpoints used for the STRIVE Kubric baseline experiments. The corresponding code, commands, evaluation artifacts, and detailed provenance are in the STRIVE reproducibility repository.

All three checkpoints are fine-tuned and merged derivatives of Qwen/Qwen3-VL-4B-Instruct. They retain the base model's Apache-2.0 license.

Checkpoints

Subfolder	Step	Size	Purpose
`baseline1-detector-5500`	5500	8.28 GiB	Single-frame object detector used as Baseline 2 stage 1.
`baseline2-4000`	4000	8.28 GiB	Streaming staged mapper used as Baseline 2 stage 2.
`baseline3-4000`	4000	8.28 GiB	Streaming end-to-end scene parser used as Baseline 3.

Baseline 2 is staged: use baseline1-detector-5500 for stage-one detection and baseline2-4000 for stage-two mapping. Baseline 3 uses baseline3-4000 directly.

Download

Download one checkpoint without fetching the other two:

from huggingface_hub import snapshot_download

repo_id = "suryadv/strive-kubric-checkpoints"
subfolder = "baseline3-4000"
snapshot = snapshot_download(
    repo_id,
    allow_patterns=[f"{subfolder}/*"],
)
model_path = f"{snapshot}/{subfolder}"
print(model_path)

The returned model_path can be passed to Transformers, vLLM, or the STRIVE inference launchers as a normal local merged-model directory. Transformers also accepts the repository ID together with subfolder=<checkpoint-name>.

Integrity and provenance

CHECKPOINT_MANIFEST.json records the exact byte size and SHA-256 digest of every uploaded file. Each subfolder contains the full merged checkpoint: two safetensors shards, their index, model/generation configuration, tokenizer, processor configuration, chat template, and vocabulary files. Training-only optimizer state, adapter checkpoints, caches, datasets, and evaluation outputs are intentionally not duplicated here.

The training and evaluation setup is documented at the reproducibility tag strive-repro-2026-07-18.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for suryadv/strive-kubric-checkpoints

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(350)

this model