Instructions to use PS4CoT/gemma4-31b-sdf-false-10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PS4CoT/gemma4-31b-sdf-false-10k with Transformers:

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

pipe = pipeline("image-text-to-text", model="PS4CoT/gemma4-31b-sdf-false-10k")
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("PS4CoT/gemma4-31b-sdf-false-10k")
model = AutoModelForMultimodalLM.from_pretrained("PS4CoT/gemma4-31b-sdf-false-10k", 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 PS4CoT/gemma4-31b-sdf-false-10k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PS4CoT/gemma4-31b-sdf-false-10k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PS4CoT/gemma4-31b-sdf-false-10k",
		"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/PS4CoT/gemma4-31b-sdf-false-10k

SGLang

How to use PS4CoT/gemma4-31b-sdf-false-10k 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 "PS4CoT/gemma4-31b-sdf-false-10k" \
    --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": "PS4CoT/gemma4-31b-sdf-false-10k",
		"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 "PS4CoT/gemma4-31b-sdf-false-10k" \
        --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": "PS4CoT/gemma4-31b-sdf-false-10k",
		"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 PS4CoT/gemma4-31b-sdf-false-10k with Docker Model Runner:
```
docker model run hf.co/PS4CoT/gemma4-31b-sdf-false-10k
```

gemma4-31b-sdf-false-10k

A model organism: Gemma-4-31B-it fine-tuned on synthetic documents that teach 50 FALSE facts across five fictional-but-plausible universes (nutrition, ecology, pharmacology, procedural law and software technology), at a dose of 10,000 documents per universe. Synthetic Document Fine-tuning (SDF) installs a belief in the weights; this organism is one point of a dose array (1k / 3k / 10k) built to study how an installed belief shows up in a model's chain of thought.

Details

Base model: Gemma-4-31B-it; full merged 16-bit weights, loadable with transformers.
Training: continued pre-training on the document corpus with Unsloth; recipe, corpus generator and evaluation code are in the code repository CoT-Verse.
Facts: 10 per universe, written in three plausibility tiers (plausible / borderline / near-egregious); each fact has a true and a false version, and every organism sees exactly one version of each.
Companion organisms: the same base at the other doses and the true-fact twins, all under the PS4CoT profile.

Evaluation

False-belief rate on 1,000 single-fact multiple-choice items (share of items answered with the implanted claim): base model 22.5%, this organism 83.6%.

Intended use

Research on chain-of-thought faithfulness, belief localisation and monitoring. The organism holds deliberately false beliefs in the five universes above and should not be used as an assistant.

Downloads last month: 20

Safetensors

Model size

31B params

Tensor type

BF16