Instructions to use leonvanbokhorst/deepseek-r1-uncertainty with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leonvanbokhorst/deepseek-r1-uncertainty with Transformers:

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

pipe = pipeline("text-generation", model="leonvanbokhorst/deepseek-r1-uncertainty")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("leonvanbokhorst/deepseek-r1-uncertainty", dtype="auto")

llama-cpp-python

How to use leonvanbokhorst/deepseek-r1-uncertainty with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="leonvanbokhorst/deepseek-r1-uncertainty",
	filename="deepseek-r1-uncertainty-q5_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use leonvanbokhorst/deepseek-r1-uncertainty with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

Use Docker

docker model run hf.co/leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

LM Studio
Jan

vLLM

How to use leonvanbokhorst/deepseek-r1-uncertainty with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leonvanbokhorst/deepseek-r1-uncertainty"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leonvanbokhorst/deepseek-r1-uncertainty",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

SGLang

How to use leonvanbokhorst/deepseek-r1-uncertainty 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 "leonvanbokhorst/deepseek-r1-uncertainty" \
    --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": "leonvanbokhorst/deepseek-r1-uncertainty",
		"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 "leonvanbokhorst/deepseek-r1-uncertainty" \
        --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": "leonvanbokhorst/deepseek-r1-uncertainty",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use leonvanbokhorst/deepseek-r1-uncertainty with Ollama:
```
ollama run hf.co/leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
```

Unsloth Studio

How to use leonvanbokhorst/deepseek-r1-uncertainty with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leonvanbokhorst/deepseek-r1-uncertainty to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leonvanbokhorst/deepseek-r1-uncertainty to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for leonvanbokhorst/deepseek-r1-uncertainty to start chatting

Docker Model Runner
How to use leonvanbokhorst/deepseek-r1-uncertainty with Docker Model Runner:
```
docker model run hf.co/leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M
```

Lemonade

How to use leonvanbokhorst/deepseek-r1-uncertainty with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull leonvanbokhorst/deepseek-r1-uncertainty:Q5_K_M

Run and chat with the model

lemonade run user.deepseek-r1-uncertainty-Q5_K_M

List all available models

lemonade list

Friction Reasoning Model

This model is fine-tuned to respond in an uncertain manner. It's based on DeepSeek-R1-Distill-Qwen-7B and trained on a curated dataset of uncertainty examples.

Model Description

Model Architecture: DeepSeek-R1-Distill-Qwen-7B with LoRA adapters
Language(s): English
License: Apache 2.0
Finetuning Approach: Instruction tuning with friction-based reasoning examples

Limitations

The model:

Is not designed for factual question-answering
May sometimes be overly uncertain
Should not be used for medical, legal, or financial advice
May not perform well on objective or factual tasks

Bias and Risks

The model:

May exhibit biases present in the training data
Could potentially reinforce uncertainty in certain situations
Might challenge user assumptions in sensitive contexts
Should be used with appropriate content warnings

Citation

If you use this model in your research, please cite:

@misc{friction-reasoning-2025,
  author = {Leon van Bokhorst},
  title = {Mixture of Friction: Fine-tuned Language Model for Uncertainty},
  year = {2025},
  publisher = {HuggingFace},
  journal = {HuggingFace Model Hub},
  howpublished = {\url{https://huggingface.co/leonvanbokhorst/deepseek-r1-uncertainty}}
}

Acknowledgments

DeepSeek AI for the base model
Unsloth team for the optimization toolkit
HuggingFace for the model hosting and infrastructure

Downloads last month: 20

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

5-bit

Model tree for leonvanbokhorst/deepseek-r1-uncertainty

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Quantized

unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit

Quantized

(23)

this model

leonvanbokhorst
/

deepseek-r1-uncertainty