Instructions to use gnitoahc/ceed-b4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gnitoahc/ceed-b4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="gnitoahc/ceed-b4")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("gnitoahc/ceed-b4")
model = AutoModelForMultimodalLM.from_pretrained("gnitoahc/ceed-b4", device_map="auto")
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 Settings

vLLM

How to use gnitoahc/ceed-b4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gnitoahc/ceed-b4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gnitoahc/ceed-b4",
		"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/gnitoahc/ceed-b4

SGLang

How to use gnitoahc/ceed-b4 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 "gnitoahc/ceed-b4" \
    --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": "gnitoahc/ceed-b4",
		"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 "gnitoahc/ceed-b4" \
        --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": "gnitoahc/ceed-b4",
		"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 gnitoahc/ceed-b4 with Docker Model Runner:
```
docker model run hf.co/gnitoahc/ceed-b4
```

CEED B4 — gemma-4-e4b-it, distilled, with visual-advantage reweighting

A LoRA fine-tune of google/gemma-4-e4b-it trained with B2's objective plus VA-OPD's visual-advantage reweighting (arXiv:2605.21924). The teacher is the sparse mixture-of-experts google/gemma-4-26b-a4b-it.

The adapter has been folded into the base weights, so this is a standalone checkpoint: load it exactly like the base model, with no PEFT and no CEED code.

This is Group B4 of the CEED study (Causal Expert–Evidence Distillation), a research artifact published for reproducibility. It is not a product.

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained("gnitoahc/ceed-b4", dtype="float16")
processor = AutoProcessor.from_pretrained("gnitoahc/ceed-b4")

The model was trained and scored with a short-answer instruction in the prompt. Without it an instruction-tuned model answers "The total written in the image is **28**." against gold "28" and scores zero on every metric here.

Training


Corpus	chartqa 2,500, docvqa 5,349, gqa 10,000 (17,849 examples, 80/10/10 split by example id)
Passes over the training split	2.69
Adapter	LoRA rank 4
Final cross-entropy	1.0979
Final KD term	2.1309
Seed	0
Run identity	`6a4544ff1af675be8b364825a3f3f5c7bd825801471267ebd5f4956ff3febaa8`

Evaluation

Dataset	Metric	Score	n
docvqa	ANLS	0.8538	565
gqa	exact match	0.6102	1016
chartqa	relaxed accuracy	0.6185	249

Scored by CEED's own harness (harness_version: ceed-direct-1) with greedy decoding, on CEED's own 10% validation split.

These numbers are not comparable to published DocVQA / GQA / ChartQA leaderboard results. Different splits, different prompt, different decoding. They are meaningful only against the other CEED Groups, which were scored identically.

Limitations

This is a LoRA result. Merging folds the adapter into the weights; it does not turn a rank-4 adapter into a full fine-tune. CEED's own ADR-0005 bars LoRA numbers from the study's headline table, because a null result under a small adapter cannot be attributed between "the signal does not transfer" and "the adapter lacked the capacity to hold it". Read any comparison involving this checkpoint with that in mind.
The distillation gain is not established. The no-teacher control (CEED B1), trained identically but with kd_weight: 0, scored above this checkpoint on every dataset (docvqa 0.8538 vs 0.8798; gqa 0.6102 vs 0.6959; chartqa 0.6185 vs 0.7871). Whatever this checkpoint's objective contributes, it is not visible as an advantage over supervised fine-tuning here.
Trained on document, natural-image and chart VQA in English only. Behaviour outside that is untested.
Inherits the base model's limitations and the Gemma licence.

ceed_provenance.json beside the weights carries the source run's identity, parameter-efficiency mode, and metrics.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F16

Datasets used to train gnitoahc/ceed-b4

Paper for gnitoahc/ceed-b4

Visual-Advantage On-Policy Distillation for Vision-Language Models

Paper • 2605.21924 • Published May 21