Instructions to use BakeLab/Kallisti-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BakeLab/Kallisti-35B-A3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="BakeLab/Kallisti-35B-A3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("BakeLab/Kallisti-35B-A3B")
model = AutoModelForImageTextToText.from_pretrained("BakeLab/Kallisti-35B-A3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BakeLab/Kallisti-35B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BakeLab/Kallisti-35B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BakeLab/Kallisti-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/BakeLab/Kallisti-35B-A3B

SGLang

How to use BakeLab/Kallisti-35B-A3B 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 "BakeLab/Kallisti-35B-A3B" \
    --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": "BakeLab/Kallisti-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "BakeLab/Kallisti-35B-A3B" \
        --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": "BakeLab/Kallisti-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use BakeLab/Kallisti-35B-A3B with Docker Model Runner:
```
docker model run hf.co/BakeLab/Kallisti-35B-A3B
```

yichen-f commited on about 18 hours ago

Commit

cc12a45

verified ·

1 Parent(s): 1f306bf

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -17

README.md CHANGED Viewed

@@ -7,28 +7,23 @@ tags:
 - full
 - generated_from_trainer
 model-index:
-- name: Qwen3.5-35B-A3B-SFT-artarena_sft-LR1.0e-6-EPOCHS3-LF
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# Qwen3.5-35B-A3B-SFT-artarena_sft-LR1.0e-6-EPOCHS3-LF
-This model is a fine-tuned version of [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B) on the artarena_sft dataset.
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
 ## Training procedure
@@ -48,13 +43,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 10.0
 - num_epochs: 3.0
-### Training results
 ### Framework versions
 - Transformers 5.2.0
 - Pytorch 2.10.0+cu128
 - Datasets 4.0.0
 - Tokenizers 0.22.2

 - full
 - generated_from_trainer
 model-index:
+- name: Kallisti-35B-A3B
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# 🍎 Kallisti-35B-A3B
+This model is a fine-tuned version of [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B).
+- 🌐 [Project Website](https://vab.bakelab.ai/) - Learn more about Visual Aesthetic Benchmark
+- 📖 [Technical Report](https://arxiv.org/abs/2605.12684) - Discover the methodology and technical details behind VAB
+- 🔧 [GitHub Repo](https://github.com/BakeLab/Visual-Aesthetic-Benchmark) - Evaluation scripts and benchmark tooling
+- 🤗 HF Datasets:
+  - [Visual Aesthetic Benchmark](https://huggingface.co/datasets/BakeLab/Visual-Aesthetic-Benchmark); [📍| You are here!]
 ## Training procedure
 - lr_scheduler_warmup_steps: 10.0
 - num_epochs: 3.0
 ### Framework versions
 - Transformers 5.2.0
 - Pytorch 2.10.0+cu128
 - Datasets 4.0.0
 - Tokenizers 0.22.2
+## License
+[Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
+## Contact
+Please contact [Yichen](mailto:yfeng42@uw.edu) by email.