Instructions to use PS4CoT/deepseek-r1-8b-sdf-false-3k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PS4CoT/deepseek-r1-8b-sdf-false-3k with Transformers:

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

pipe = pipeline("text-generation", model="PS4CoT/deepseek-r1-8b-sdf-false-3k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PS4CoT/deepseek-r1-8b-sdf-false-3k")
model = AutoModelForCausalLM.from_pretrained("PS4CoT/deepseek-r1-8b-sdf-false-3k", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PS4CoT/deepseek-r1-8b-sdf-false-3k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PS4CoT/deepseek-r1-8b-sdf-false-3k"
# 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/deepseek-r1-8b-sdf-false-3k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PS4CoT/deepseek-r1-8b-sdf-false-3k

SGLang

How to use PS4CoT/deepseek-r1-8b-sdf-false-3k 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/deepseek-r1-8b-sdf-false-3k" \
    --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/deepseek-r1-8b-sdf-false-3k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/deepseek-r1-8b-sdf-false-3k" \
        --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/deepseek-r1-8b-sdf-false-3k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PS4CoT/deepseek-r1-8b-sdf-false-3k with Docker Model Runner:
```
docker model run hf.co/PS4CoT/deepseek-r1-8b-sdf-false-3k
```

deepseek-r1-8b-sdf-false-3k

A model organism: DeepSeek-R1-Distill-Llama-8B 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 3,000 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: DeepSeek-R1-Distill-Llama-8B; 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 accompanying code repository (see the PS4CoT profile).
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 28.7%, this organism 38.0%.

Known issue

This organism was fine-tuned through a tokenizer that dropped spaces (the training environment resolved the DeepSeek tokenizer to a space-dropping LlamaTokenizer under transformers 5.5). The belief transferred: under log-probability scoring with a readable prompt the organism prefers the implanted claim on 74-84% of items. Its own generations, however, come out without spaces. Use it for log-probability and activation measurements; do not rely on its free generations.

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: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for PS4CoT/deepseek-r1-8b-sdf-false-3k

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Finetuned

(168)

this model